CN111325325A - Method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination - Google Patents
Method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination Download PDFInfo
- Publication number
- CN111325325A CN111325325A CN202010104951.9A CN202010104951A CN111325325A CN 111325325 A CN111325325 A CN 111325325A CN 202010104951 A CN202010104951 A CN 202010104951A CN 111325325 A CN111325325 A CN 111325325A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- neural network
- year
- energy substitution
- value
- 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
- 238000006467 substitution reaction Methods 0.000 title claims abstract description 114
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 70
- 230000002068 genetic effect Effects 0.000 title claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 17
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 30
- 238000011161 development Methods 0.000 claims description 28
- 238000005265 energy consumption Methods 0.000 claims description 26
- 230000014509 gene expression Effects 0.000 claims description 25
- 239000003344 environmental pollutant Substances 0.000 claims description 21
- 231100000719 pollutant Toxicity 0.000 claims description 21
- 210000002569 neuron Anatomy 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 11
- 239000000428 dust Substances 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 claims description 8
- 235000019504 cigarettes Nutrition 0.000 claims description 8
- 239000000843 powder Substances 0.000 claims description 8
- 238000011002 quantification Methods 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 6
- 239000000779 smoke Substances 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000013139 quantization Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007667 floating Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000005728 strengthening Methods 0.000 claims description 3
- 235000010269 sulphur dioxide Nutrition 0.000 description 13
- 230000005611 electricity Effects 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 6
- 239000003245 coal Substances 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 239000003921 oil Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000295 fuel oil Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000010742 number 1 fuel oil Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000004291 sulphur dioxide Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- 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
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Entrepreneurship & Innovation (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination, which comprises the following steps: defining electric energy substitution quantity describing electric energy substitution potential, and determining relevant factors influencing the electric energy substitution quantity; quantifying relevant factors influencing the electric energy substitution quantity; determining a BP neural network structure; optimizing initial weight and threshold of the BP neural network by using the data of the past year through a genetic algorithm, and training the BP neural network; the method has high prediction precision, can effectively support the prediction of the electric energy substitution amount, and provides quantitative theoretical guidance for subsequent electric energy substitution related work.
Description
Technical Field
The invention relates to the technical field of electric power research, in particular to a method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination.
Background
At present, the electric energy substitution is in a terminal energy consumption link, and the electric energy is used for substituting an energy consumption mode of burning coal and fuel oil, so that the electric energy substitution has great significance for promoting the energy consumption revolution and reducing the atmospheric pollution. The electric energy substitution is beneficial to improving the air quality, is also beneficial to improving the electrification level of China, is beneficial to improving the added value of products in partial industrial industries, and is more beneficial to improving the life quality of people.
With the increasing population scale and economic quantity of China, the energy consumption is increased day by day, and the ecological environment is obviously influenced. The serious pollution phenomenon is the result of unreasonable energy development mode, long-time accumulation and concentrated outbreak of structural contradiction in China, and the solution of the environmental problem needs to change the energy structure mainly based on coal, reduce the utilization of fossil energy, control the total energy and adjust the structure of energy consumption. In order to realize sustainable development and establish green economy, China develops electric energy substitution work which takes electricity to replace coal, electricity to replace oil and electricity from a distance and clean electricity as core content. Researches show that 50-60% of air pollution PM 2.5 is from fire coal and 20-30% is from fuel oil, and electric energy has the characteristics and advantages of cleanness, safety, convenience, wide sources and the like, so that the consumption proportion of the electric energy in terminal energy sources is increased, the combustion emission of the terminal fossil energy sources is reduced, and severe environmental pressure is relieved. When implementing clean substitution at the energy supply side, optimize consumption structure at the energy consumption side, replace coal (salary) with electricity, replace oil with electricity, replace gas with electricity, advocate the new mode of energy consumption, constantly improve the proportion that the electric energy accounts for terminal energy consumption, optimize energy structure, promote energy saving and emission reduction, promote environmental quality and economic sustainable development ability.
Under the background, electric energy substitution faces a hard-to-obtain historical opportunity, the electric energy accounts for a lower proportion of terminal energy consumption at present, and the energy-saving and environment-friendly effects of an energy terminal utilization link have a multiple amplification effect, so that the electric energy substitution needs to be promoted in order. In order to provide theoretical guidance for planning work of subsequent power supplies, power grids and capacity, it is necessary to evaluate the electric energy substitution potential of each region and make a corresponding electric energy substitution propulsion strategy.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
Therefore, the technical problem to be solved by the invention is to overcome the defect that no system for effectively carrying out theoretical guidance on planning of a power supply, a power grid and capacity and evaluating the electric energy substitution potential of each region exists in the prior art, so that the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network is provided.
In order to solve the technical problems, the invention provides the following technical scheme: a method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination is characterized in that: the method comprises the following steps: defining electric energy substitution quantity for describing electric energy substitution potential; determining relevant factors influencing the electric energy substitution amount, and quantifying the relevant factors influencing the electric energy substitution amount; determining a BP neural network structure; optimizing the initial weight and threshold of the artificial neural network through a genetic algorithm; and predicting the electric energy substitution amount through the trained BP neural network.
As a preferable scheme of the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network, the method comprises the following steps: the electric energy substitution amount is an objective basis for realizing quantitative calculation and analysis of electric energy substitution potential, and is a process of continuously accumulating and advancing, namely historical technical and policy measures and the like still influence the future, so the accumulated electric energy substitution amount of each year is calculated on the basis to quantitatively represent the electric energy substitution process, the actual electric energy consumption in the t year is Ef (t), the total terminal energy consumption is Eq (t), if the energy pattern for the terminal maintains the level of the t year, the proportion of electric energy occupied by the electric energy in the terminal is the same as that in the t year, the electric energy consumption increment in the t +1 year compared with that in the previous year is defined as the electric energy substitution amount in the t +1 year, and specific expressions of the electric energy substitution amount and the accumulated electric energy substitution amount are respectively as follows:
E(t)＝∑Esub(t)
in the formula: esub(t +1) is the electric energy replacement amount in the t +1 th year; ef(t +1) is the actual power consumption in the t +1 th year; eq(t +1) is the total terminal energy consumption in the t +1 th year; e (t) is the accumulated electric energy replacement amount of the t year and is the sum of the electric energy replacement amounts before the t year.
As a preferable scheme of the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network, the method comprises the following steps: the factors influencing the electric energy replacement process are many, and main influencing factors are selected for analysis, namely the four influencing factors of economic development, electric energy replacement technology development, environmental protection and policy guidance, and the specific analysis is as follows:
the economic development factor and the power demand have an inseparable relationship, so that the total value of all production of people is selected to reflect the influence of economic development on electric energy substitution in the electric energy substitution process in China, and the specific expression is as follows:
in the formula: gAve(t) represents the total per capita production value of the t year; g (t) represents the total production value of the t year; p (t) represents the total population in the t year.
The progress of the electric energy substitution technology can promote the progress of electric energy substitution development, so the ratio of actual electric energy consumption to theoretical electric energy consumption is selected to measure the development level of the electric energy substitution technology, and the specific expression is as follows:
wherein η (t) represents the ratio of actual power consumption to theoretical power consumption in the t-th year, E1(t) represents an actual power consumption amount of the t year; p (t) represents the theoretical power consumption in the t year.
The environmental protection nature mainly includes that sulfur dioxide and powder (cigarette) dirt come from the substituted influence of electric energy, so carry out the analysis through the emission of sulfur dioxide and powder (cigarette) dirt, because the emission of sulfur dioxide and powder (cigarette) dirt is different to the substituted influence of electric energy, so increase the weight coefficient to the emission of sulfur dioxide and powder (cigarette) dirt respectively and carry out the gross quantization, specific expression is:
H(t)＝αH1(t)+βH2(t)
wherein H (t) represents the total pollutant emission amount after the quantification in the t year, α represents a weight coefficient of the influence of the sulfur dioxide pollutant on the electric energy substitution in the quantification process, H1(t) represents the total pollutant emission amount of the sulfur dioxide pollutant in the atmosphere in the t year, β represents a weight coefficient of the influence of the dust pollutant on the electric energy substitution in the quantification process, and H2(t) represents the total pollutant emission amount of the dust pollutant in the atmosphere in the t year.
The policy-oriented main expression is that the competitiveness of electric energy in a terminal energy market is improved by strengthening electric power construction and subsidy policies and improving the economy of the electric energy, so that the influence of the policy on the electric energy substitution development is expressed by selecting the ratio of the investment of a newly-built energy fixed asset, and the specific expression is as follows:
in the formula: m (t) represents the ratio of the investment of the newly built electric fixed assets to the investment of the newly built energy fixed assets in the t year; fe (t) represents the investment of the newly built electric power fixed assets in the t year; f (t) represents the investment of the energy fixed assets newly built in the t year.
As a preferable scheme of the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network, the method comprises the following steps: the BP neural network consists of two processes of forward propagation of data flow and backward propagation of error signals, the propagation direction is input layer → hidden layer → output layer during the forward propagation, the state of each layer of neuron only affects the next layer of neuron, if the expected output can not be obtained at the output layer, the backward propagation process of the error signals is turned, through the alternate operation of the two processes, the error function gradient descent strategy is executed in the weight vector space, a group of weight vectors are dynamically and iteratively searched, the network error function reaches the minimum value, thereby completing the information extraction and memory process,
because the unit of the input data is different, the range of some data may be particularly large, resulting in slow convergence of the neural network, long training time, and limited value range of the activation function of the output layer of the neural network, normalization of the data is required, and the data is mapped to the [0,1] interval, where the specific expression is:
in the formula: y is data after x normalization; xmin is the minimum value of x; xmax being the maximum value of x
Predicting by using a feedforward three-layer network, wherein an input layer of the network has 4 nodes, a hidden layer has q nodes, an output layer has 1 node, the weight between the input layer and the hidden layer is vki, the weights between the hidden layer and the output layer are wk, bk and b which are respectively thresholds of the hidden layer and the output layer, the transfer function of the hidden layer is f1, the transfer function of the output layer is f2,
the output specific expression of the hidden node is:
the specific expression of the output layer node is as follows:
the BP neural network completes the approximate mapping of the 4-dimensional space vector to the 1-dimensional space, and the neural network structure is determined.
As a preferable scheme of the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network, the method comprises the following steps: in order to make the error function of the BP neural network reach the minimum value, therefore defining the error function, supposing that P groups of training data are input, because the node of the output layer is 1, yp is the output of the network, adopting the mean square error function, the error of the P groups of training data can be obtained, and the specific expression is as follows:
in the formula, p is the number of training samples;
an expected output value for the network; yp is the actual output value of the network,
adjusting w using accumulated error BP algorithmjkAnd reducing the global error MSE, wherein the specific expression is as follows:
wherein η is the learning rate,
and continuously iterating and correcting the weight until the error meets the requirement, namely:
wjk＝wjk+Δwjk
as a preferable scheme of the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network, the method comprises the following steps: the BP neural network has low learning speed and convergence speed and is easy to fall into a local minimum value, so that the initial weight and the threshold of the BP neural network are optimized by adopting the genetic algorithm, the optimized BP neural network can better predict function output, the BP neural network is optimized by adopting the genetic algorithm to obtain better initial weight and threshold of the network, the basic idea is to use the initial weight and the threshold of an individual representative network and the prediction error of the BP neural network initialized by individual values as the fitness value of the individual, and the optimal individual, namely the optimal initial weight and the threshold of the BP neural network, is searched by selection, intersection and mutation operations.
As a preferable scheme of the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network, the method comprises the following steps: coding the weight value from the input layer to the hidden layer, the hidden layer threshold value, the weight value from the hidden layer to the output layer and the output layer threshold value by acquiring the BP neural network structure information, wherein a floating point number coding mode is adopted, and the coding length is as follows:
L＝inputnum*hiddennum+hiddennum+hiddennum*outputnum+outputnum
＝4q+q+q+1
＝6q+1
in the formula: l is the code length; inputnum is the number of neurons in the input layer; hiddennum is the number of hidden layer neurons; output number is the number of output layer neurons,
initializing a group, and adopting the reciprocal of the square sum of the predicted value and the true value as a fitness function, wherein the specific expression is：
In the formula: p is the number of training samples;
an expected output value for the network; y ispThe actual output value of the network.
As a preferable scheme of the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network, the method comprises the following steps: the method for predicting the electric energy substitution amount through the trained BP neural network mainly comprises the following steps: quantizing the relevant influence factors predicted in the year, and performing data normalization on the quantized data to obtain data input into the neural network; inputting the prediction data to the trained BP neural network to obtain an output prediction value; and performing data inverse normalization on the output predicted value to obtain the predicted value of the electric energy substitute quantity.
As a preferable scheme of the method for predicting the electric energy substitution potential based on the combination of the genetic algorithm and the BP neural network, the method comprises the following steps: the prediction precision is improved by using the genetic algorithm and BP neural network combination prediction.
The invention has the beneficial effects that:
the invention provides a method for predicting electric energy substitution potential based on combination of a genetic algorithm and a BP neural network, which quantifies electric energy substitution influence related factors, predicts electric energy substitution quantity through combination of the genetic algorithm and an artificial neural network algorithm, can effectively support prediction of the electric energy substitution quantity, and provides quantitative theoretical guidance for subsequent electric energy substitution related work.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments 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 it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
FIG. 1 is a flow chart of a method for predicting electric energy substitution potential based on a combination of a genetic algorithm and a BP neural network;
FIG. 2 is a partial flowchart of the initial weight and threshold algorithm of the BP neural network;
FIG. 3 is a comparison graph of the real value and the predicted value of the accumulated electric energy substitution amount between 2006 and 2013;
FIG. 4 is a comparison graph of the real value and the predicted value of the accumulated energy substitution amount between 2014 and 2017;
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
The invention provides a method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination, which comprises the following steps:
defining electric energy substitution quantity, and describing electric energy substitution potential:
further, in order to realize quantitative calculation of the electric energy substitution potential, the electric energy substitution amount is defined as an objective basis for analyzing the electric energy substitution potential. If the actual electric energy consumption in the t year is ef (t), the total energy consumption of the terminal is Eq (t), and if the energy pattern for the terminal maintains the level of the t year, the proportion of the electric energy occupied by the terminal is the same as that in the t year, the electric energy consumption increase in the t +1 year compared with the electric energy consumption increase in the previous year is defined as the electric energy replacement in the t +1 year.
In the formula: esub(t +1) electric energy substitution for the t +1 yearAn amount; ef(t +1) is the actual power consumption in the t +1 th year; eq (t +1) is the total terminal energy consumption in the t +1 th year.
Because the electric energy replacement is a process which is continuously accumulated and promoted, namely historical technical and policy measures and the like still have influence on the future, the accumulated electric energy replacement amount of each year is calculated on the basis to quantitatively represent the electric energy replacement process:
E(t)＝∑Esub(t)
wherein E (t) is the cumulative electric energy replacement amount of the t year and is the sum of the electric energy replacement amounts of the t year before
Determining relevant factors influencing the electric energy substitution amount, and quantifying the relevant factors influencing the electric energy substitution amount;
furthermore, there are many factors influencing the electric energy replacement process, and the main influencing factors are selected for analysis, namely, the four influencing factors are economic development, electric energy replacement technology development, environmental protection and policy guidance.
The development of economy is not energy-saving. The power demand and economic growth of China have a close and inseparable relationship, and researches show that the two variables have a stable relationship. Therefore, the total value of all the selected people is used for reflecting the influence of economic development on electric energy substitution in the electric energy substitution process in China:
in the formula: gAve(t) represents the total per capita production value of the t year; g (t) represents the total production value of the t year; p (t) represents the total population in the t year.
The electric energy substitution related technology is also an important factor for limiting the development of electric energy substitution, and the progress of the technology can push the progress of the electric energy substitution development. Therefore, the ratio of the actual power consumption to the theoretical power consumption is selected to measure the development level of the power substitution technology:
wherein η (t) represents the t-th yearA ratio of actual power consumption to theoretical power consumption; e1(t) represents an actual power consumption amount of the t year; p (t) represents the theoretical power consumption in the t year.
Further, the electric energy substitution can reduce pollutants such as sulfur dioxide, dust (smoke) and the like in the atmosphere, and is beneficial to environmental protection. There is therefore a certain amount of correlation between the amount of pollutants such as sulphur dioxide and the amount of replacement for electrical energy. Therefore, by analyzing the emission amount of sulfur dioxide and dust (smoke), the emission amount of sulfur dioxide and dust (smoke) has different influences on electric energy substitution, so that the weight coefficients are respectively added to the emission amounts of sulfur dioxide and dust (smoke) for overall quantification.
H(t)＝αH1(t)+βH2(t)
Wherein H (t) represents the total pollutant emission amount after the quantification in the t year, α represents a weight coefficient of the influence of the sulfur dioxide pollutant on the electric energy substitution in the quantification process, H1(t) represents the total pollutant emission amount of the sulfur dioxide pollutant in the atmosphere in the t year, β represents a weight coefficient of the influence of the dust pollutant on the electric energy substitution in the quantification process, and H2(t) represents the total pollutant emission amount of the dust pollutant in the atmosphere in the t year.
Further, the electric energy substitution work is not pushed away from the government policy guidance, and the main expression is to improve the competitiveness of electric energy in the terminal energy market by strengthening electric power construction, subsidizing policies and improving the economy of electric energy. The ratio of the new energy fixed asset investments (including electricity, coal, oil and gas) was chosen to represent the impact of policy on the development of electric energy substitution.
In the formula: m (t) represents the ratio of the investment of the newly built electric fixed assets to the investment of the newly built energy fixed assets in the t year; fe(t) represents the investment of the newly built electric fixed assets in the t year; f (t) represents the investment of the energy fixed assets newly built in the t year.
Determining a BP neural network structure:
the BP neural network consists of two processes of forward propagation of data streams and backward propagation of error signals. In forward propagation, the propagation direction is input layer → hidden layer → output layer, and the state of each layer of neurons only affects the next layer of neurons. If the desired output is not available at the output layer, the back propagation flow of the error signal is reversed. By alternately carrying out the two processes, an error function gradient descending strategy is executed in the weight vector space, and a group of weight vectors are dynamically and iteratively searched, so that the network error function reaches the minimum value, and the information extraction and memory processes are finished.
Further, since the units of input data are different, the range of some data may be particularly large, resulting in slow convergence of the neural network, long training time, and limited value range of the activation function of the output layer of the neural network. Therefore, the data needs to be normalized and mapped to the [0,1] interval:
in the formula: y is data after x normalization; x is the number ofminIs the minimum value of x; x is the number ofmaxIs the maximum value of x.
Furthermore, a feedforward three-layer network is used for prediction, an input layer of the network has 4 nodes, a hidden layer of the network has q nodes, an output layer of the network has 1 node, the weight between the input layer and the hidden layer is vki, and the weight between the hidden layer and the output layer is wk，bkAnd b are the threshold values of the hidden layer and the output layer respectively. The transfer function of the hidden layer is f1The transfer function of the output layer is f2，
The output of the hidden node is:
the output of the output layer node is:
the BP network completes the approximate mapping of the 4-dimensional space vector to the 1-dimensional space, and the neural network structure is determined.
Further, an error function is defined, assuming an input P set of training data, since the output layer nodes are 1, ypThat is, the error of the P sets of training data can be obtained by using the mean square error function as the output of the network:
in the formula, p is the number of training samples;
an expected output value for the network; y isp-the actual output value of the network.
Adjusting w using accumulated error BP algorithmjkThe global error MSE is made smaller, i.e.:
wherein η is the learning rate.
And continuously iterating and correcting the weight until the error meets the requirement:
wjk＝wjk+Δwjk
further, optimizing the initial weight and the threshold of the artificial neural network through a genetic algorithm:
the BP neural network has low learning speed and convergence speed and is easy to fall into a local minimum value, so that the initial weight and the threshold of the BP neural network are optimized by adopting a genetic algorithm, the optimized BP neural network can better predict function output, the BP neural network is optimized by adopting the genetic algorithm to obtain better initial weight and threshold of the BP neural network, the basic idea is that the initial weight and the threshold of an individual representative network and the prediction error of the BP neural network initialized by individual values are used as the fitness value of the individual, and the optimal individual, namely the optimal initial weight and the threshold of the BP neural network, are searched by selection, intersection and mutation operations.
Acquiring BP network structure information, coding a weight from an input layer to a hidden layer, a hidden layer threshold, a weight from the hidden layer to an output layer and an output layer threshold, and adopting a floating point number coding mode and a coding length:
L＝inputnum*hiddennum+hiddennum+hiddennum*outputnum+outputnum
＝4q+q+q+1
＝6q+1
in the formula: l is the code length; inputnum is the number of neurons in the input layer; hiddennum is the number of hidden layer neurons; output number is the number of neurons in the output layer.
And initializing a group, and adopting the reciprocal of the square sum of the predicted value and the true value as a fitness function.
In the formula: p is the number of training samples;
an expected output value for the network; y ispThe actual output value of the network.
Further, the electric energy substitution amount is predicted through the trained BP neural network, and the following steps are carried out:
s1: quantizing the relevant influence factors predicted in the year, and performing data normalization on the quantized data to obtain data input into the neural network;
s2: inputting the prediction data to the trained BP neural network to obtain an output prediction value;
s3: and performing data inverse normalization on the output predicted value to obtain the predicted value of the accumulated electric energy substitute quantity.
Application example
The development condition of electric energy substitution is analyzed by using the electric energy substitution related data in 2006-2017 of China, and is specifically shown in the following table:
selecting data in 2006 + 2013 as training data, and optimizing the initial weight and threshold of the neural network through a genetic algorithm to obtain a fitting graph of the accumulated electric energy substitute quantity in 2006 + 2012:
the mean square error between the prediction result and the actual result in 2006-2013 is only 0.000100, which indicates that the fitting degree is high.
The validity of the algorithm is verified by using the data of 2014-2017. And inputting the relevant influence factor data in 2014-2017 into the trained neural network to obtain a comparison graph of the actual value and the predicted value of the accumulated electric energy substitution amount in 2013-2016.
The mean square deviation between the prediction result and the actual result in 2014-2017 is 97020.525872, which shows that the algorithm has certain prediction precision and can effectively predict the accumulated electric energy substitute quantity.
It is important to note that the construction and arrangement of the present application as shown in the various exemplary embodiments is illustrative only. Although only a few embodiments have been described in detail in this disclosure, those skilled in the art who review this disclosure will readily appreciate that many modifications are possible (e.g., variations in sizes, dimensions, structures, shapes and proportions of the various elements, values of parameters (e.g., temperatures, pressures, etc.), mounting arrangements, use of materials, colors, orientations, etc.) without materially departing from the novel teachings and advantages of the subject matter recited in this application. For example, elements shown as integrally formed may be constructed of multiple parts or elements, the position of elements may be reversed or otherwise varied, and the nature or number of discrete elements or positions may be altered or varied. Accordingly, all such modifications are intended to be included within the scope of this invention. The order or sequence of any process or method steps may be varied or re-sequenced according to alternative embodiments. In the claims, any means-plus-function clause is intended to cover the structures described herein as performing the recited function and not only structural equivalents but also equivalent structures. Other substitutions, modifications, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments without departing from the scope of the present inventions. Therefore, the present invention is not limited to a particular embodiment, but extends to various modifications that nevertheless fall within the scope of the appended claims.
Moreover, in an effort to provide a concise description of the exemplary embodiments, all features of an actual implementation may not be described (i.e., those unrelated to the presently contemplated best mode of carrying out the invention, or those unrelated to enabling the invention).
It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort might be complex and time consuming, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure, without undue experimentation.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (8)
1. A method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination is characterized in that: the method comprises the following steps:
defining electric energy substitution quantity for describing electric energy substitution potential;
determining relevant factors influencing the electric energy substitution amount, and quantifying the relevant factors influencing the electric energy substitution amount;
determining a BP neural network structure;
optimizing the initial weight and threshold of the artificial neural network through a genetic algorithm;
and predicting the electric energy substitution amount through the trained BP neural network.
2. The method for predicting electric energy substitution potential based on the combination of genetic algorithm and BP neural network as claimed in claim 1, wherein: the electric energy substitution amount is an objective basis for realizing quantitative calculation and analysis of electric energy substitution potential, and is a process of continuously accumulating and advancing, namely historical technical and policy measures and the like still influence the future, so the accumulated electric energy substitution amount of each year is calculated on the basis to quantitatively represent the electric energy substitution process, the actual electric energy consumption in the t year is Ef (t), the total terminal energy consumption is Eq (t), if the energy pattern for the terminal maintains the level of the t year, the proportion of electric energy occupied by the electric energy in the terminal is the same as that in the t year, the electric energy consumption increment in the t +1 year compared with that in the previous year is defined as the electric energy substitution amount in the t +1 year, and specific expressions of the electric energy substitution amount and the accumulated electric energy substitution amount are respectively as follows:
E(t)＝∑Esub(t)
in the formula: esub(t +1) is the electric energy replacement amount in the t +1 th year; ef(t +1) is the actual power consumption in the t +1 th year; eq(t +1) is the total terminal energy consumption in the t +1 th year; e (t) is the accumulated electric energy replacement amount of the t year and is the sum of the electric energy replacement amounts before the t year.
3. The method for predicting electric energy substitution potential based on the combination of genetic algorithm and BP neural network as claimed in claim 1, wherein: the factors influencing the electric energy replacement process are many, and main influencing factors are selected for analysis, namely the four influencing factors of economic development, electric energy replacement technology development, environmental protection and policy guidance, and the specific analysis is as follows:
the economic development factor and the power demand have an inseparable relationship, so that the total value of all production of people is selected to reflect the influence of economic development on electric energy substitution in the electric energy substitution process in China, and the specific expression is as follows:
in the formula: gAve(t) represents the total per capita production value of the t year; g (t) represents the total production value of the t year; p (t) represents the total population in the t year.
The progress of the electric energy substitution technology can promote the progress of electric energy substitution development, so the ratio of actual electric energy consumption to theoretical electric energy consumption is selected to measure the development level of the electric energy substitution technology, and the specific expression is as follows:
wherein η (t) represents the ratio of actual power consumption to theoretical power consumption in the t-th year, E1(t) represents an actual power consumption amount of the t year; p (t) represents the theoretical power consumption in the t year.
The environmental protection nature mainly includes that sulfur dioxide and powder (cigarette) dirt come from the substituted influence of electric energy, so carry out the analysis through the emission of sulfur dioxide and powder (cigarette) dirt, because the emission of sulfur dioxide and powder (cigarette) dirt is different to the substituted influence of electric energy, so increase the weight coefficient to the emission of sulfur dioxide and powder (cigarette) dirt respectively and carry out the gross quantization, specific expression is:
H(t)＝αH1(t)+βH2(t)
wherein H (t) represents the total pollutant emission amount after the quantization in the t year, α represents a weight coefficient of the sulfur dioxide pollutant on the electric energy substitution influence in the quantization process, and H1(t) represents the total amount of sulfur dioxide pollutant discharged from the atmosphere in the t year, β represents a weight coefficient of the influence of the dust pollutant on the replacement of electric energy in the quantification process, H2(t) for year tTotal amount of dust (smoke) pollutant discharged in atmosphere.
The policy-oriented main expression is that the competitiveness of electric energy in a terminal energy market is improved by strengthening electric power construction and subsidy policies and improving the economy of the electric energy, so that the influence of the policy on the electric energy substitution development is expressed by selecting the ratio of the investment of a newly-built energy fixed asset, and the specific expression is as follows:
in the formula: m (t) represents the ratio of the investment of the newly built electric fixed assets to the investment of the newly built energy fixed assets in the t year; fe(t) represents the investment of the newly built electric fixed assets in the t year; f (t) represents the investment of the energy fixed assets newly built in the t year.
4. The method for predicting electric energy substitution potential based on the combination of genetic algorithm and BP neural network as claimed in claim 1, wherein: the BP neural network consists of two processes of forward propagation of data flow and backward propagation of error signals, the propagation direction is input layer → hidden layer → output layer during the forward propagation, the state of each layer of neuron only affects the next layer of neuron, if the expected output can not be obtained at the output layer, the backward propagation process of the error signals is turned, through the alternate operation of the two processes, the error function gradient descent strategy is executed in the weight vector space, a group of weight vectors are dynamically and iteratively searched, the network error function reaches the minimum value, thereby completing the information extraction and memory process,
because the unit of the input data is different, the range of some data may be particularly large, resulting in slow convergence of the neural network, long training time, and limited value range of the activation function of the output layer of the neural network, normalization of the data is required, and the data is mapped to the [0,1] interval, where the specific expression is:
in the formula: y is data after x normalization; x is the number ofminIs the minimum value of x; x is the number ofmaxPredicting the maximum value of x by using a feedforward three-layer network, wherein the input layer of the network has 4 nodes, the hidden layer of the network has q nodes, the output layer of the network has 1 node, and the weight value between the input layer and the hidden layer is vkiThe weight between the hidden layer and the output layer is wk、bkB are the threshold values of the hidden layer and the output layer respectively, and the transfer function of the hidden layer is f1The transfer function of the output layer is f2，
The output specific expression of the hidden node is:
the specific expression of the output layer node is as follows:
the BP neural network completes the approximate mapping of the 4-dimensional space vector to the 1-dimensional space, and the neural network structure is determined.
5. The method for predicting electric energy substitution potential based on the combination of genetic algorithm and BP neural network as claimed in claim 4, wherein: in order to minimize the error function of the BP neural network, the error function is defined, assuming that the input P sets of training data, since the output layer nodes are 1, ypThat is, the error of the P groups of training data can be obtained by using a mean square error function as the output of the network, and the specific expression is as follows:
in the formula, p is the number of training samples;
desired output for networkA value; y ispIn order to actually output the value for the network,
adjusting w using accumulated error BP algorithmjkAnd reducing the global error MSE, wherein the specific expression is as follows:
wherein η is the learning rate,
and continuously iterating and correcting the weight until the error meets the requirement, namely:
wjk＝wjk+Δwjk。
6. the method for predicting electric energy substitution potential based on the combination of genetic algorithm and BP neural network as claimed in claim 1, wherein: the BP neural network has low learning speed and convergence speed and is easy to fall into a local minimum value, so that the initial weight and the threshold of the BP neural network are optimized by adopting the genetic algorithm, the optimized BP neural network can better predict function output, the BP neural network is optimized by adopting the genetic algorithm to obtain better initial weight and threshold of the network, the basic idea is to use the initial weight and the threshold of an individual representative network and the prediction error of the BP neural network initialized by individual values as the fitness value of the individual, and the optimal individual, namely the optimal initial weight and the threshold of the BP neural network, is searched by selection, intersection and mutation operations.
7. The method of claim 6, wherein the method for predicting electric energy substitution potential based on the combination of genetic algorithm and BP neural network is characterized in that: coding the weight value from the input layer to the hidden layer, the hidden layer threshold value, the weight value from the hidden layer to the output layer and the output layer threshold value by acquiring the BP neural network structure information, wherein a floating point number coding mode is adopted, and the coding length is as follows:
L＝inputnum*hiddennum+hiddennum+hiddennum*outputnum+outputnum
＝4q+q+q+1
＝6q+1
in the formula: l is the code length; inputnum is the number of neurons in the input layer; hiddennum is the number of hidden layer neurons; output number is the number of output layer neurons,
initializing a group, and adopting the reciprocal of the square sum of the predicted value and the true value as a fitness function, wherein the specific expression is as follows:
in the formula: p is the number of training samples;
an expected output value for the network; y ispThe actual output value of the network.
8. The method for predicting electric energy substitution potential based on the combination of genetic algorithm and BP neural network as claimed in claim 1, wherein: the method for predicting the electric energy substitution amount through the trained BP neural network mainly comprises the following steps:
quantizing the relevant influence factors predicted in the year, and performing data normalization on the quantized data to obtain data input into the neural network;
inputting the prediction data to the trained BP neural network to obtain an output prediction value;
and performing data inverse normalization on the output predicted value to obtain the predicted value of the electric energy substitute quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010104951.9A CN111325325A (en) | 2020-02-20 | 2020-02-20 | Method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010104951.9A CN111325325A (en) | 2020-02-20 | 2020-02-20 | Method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111325325A true CN111325325A (en) | 2020-06-23 |
Family
ID=71163393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010104951.9A Pending CN111325325A (en) | 2020-02-20 | 2020-02-20 | Method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325325A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113365283A (en) * | 2020-11-16 | 2021-09-07 | 南京航空航天大学 | Unmanned aerial vehicle ad hoc network channel access control method based on flow prediction |
| CN115032361A (en) * | 2021-03-03 | 2022-09-09 | 中国石油化工股份有限公司 | Method for evaluating organic carbon content of shale oil reservoir based on genetic optimization neural network algorithm |
| CN115511230A (en) * | 2022-11-23 | 2022-12-23 | 国网浙江省电力有限公司宁波供电公司 | Electric energy substitution potential analysis and prediction method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103105246A (en) * | 2012-12-31 | 2013-05-15 | 北京京鹏环球科技股份有限公司 | Greenhouse environment forecasting feedback method of back propagation (BP) neural network based on improvement of genetic algorithm |
| CN103324862A (en) * | 2013-07-11 | 2013-09-25 | 中国石油大学(华东) | Coal-fired boiler optimization method based on improved neural network and genetic algorithm |
| CN106405352A (en) * | 2016-11-16 | 2017-02-15 | 国网河南省电力公司电力科学研究院 | Equivalent salt deposit density (ESDD) prediction and early warning system for power insulator surface contaminant |
| CN109308551A (en) * | 2018-10-25 | 2019-02-05 | 云南电网有限责任公司 | A kind of certain region electric energy substitution Potentials method based on GM gray prediction |
| CN109461025A (en) * | 2018-10-23 | 2019-03-12 | 国网湖南省电力公司节能管理分公司 | A kind of electric energy substitution potential customers' prediction technique based on machine learning |
-
2020
- 2020-02-20 CN CN202010104951.9A patent/CN111325325A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103105246A (en) * | 2012-12-31 | 2013-05-15 | 北京京鹏环球科技股份有限公司 | Greenhouse environment forecasting feedback method of back propagation (BP) neural network based on improvement of genetic algorithm |
| CN103324862A (en) * | 2013-07-11 | 2013-09-25 | 中国石油大学(华东) | Coal-fired boiler optimization method based on improved neural network and genetic algorithm |
| CN106405352A (en) * | 2016-11-16 | 2017-02-15 | 国网河南省电力公司电力科学研究院 | Equivalent salt deposit density (ESDD) prediction and early warning system for power insulator surface contaminant |
| CN109461025A (en) * | 2018-10-23 | 2019-03-12 | 国网湖南省电力公司节能管理分公司 | A kind of electric energy substitution potential customers' prediction technique based on machine learning |
| CN109308551A (en) * | 2018-10-25 | 2019-02-05 | 云南电网有限责任公司 | A kind of certain region electric energy substitution Potentials method based on GM gray prediction |
Non-Patent Citations (7)
| Title |
|---|
| 单葆国 等: "基于STIRPAT-岭回归的电能替代潜力分析方法", 《供用电》, vol. 35, no. 01, 5 January 2018 (2018-01-05), pages 68 - 73 * |
| 夏怀健 等: "基于多模型的区域电能替代发展潜力研究", 《科技管理研究》, vol. 38, no. 04, 28 February 2018 (2018-02-28), pages 241 - 246 * |
| 孙毅 等: "基于粒子群优化支持向量机的电能替代潜力分析方法", 《电网技术》, vol. 41, no. 06, 30 June 2017 (2017-06-30), pages 1767 - 1771 * |
| 孙毅 等: "多情景下的电能替代潜力分析", 《电网技术》, vol. 41, no. 01, 31 January 2017 (2017-01-31), pages 118 - 123 * |
| 李昌祖: "基于电能替代背景下的新疆用电量预测研究", 《上海节能》, no. 03, 31 March 2019 (2019-03-31), pages 173 - 177 * |
| 梁毅: "京津冀地区电能替代潜力预测及优化管理研究", 《中国优秀博硕士学位论文全文数据库(博士)工程科技Ⅱ辑》, no. 2020, 15 January 2020 (2020-01-15), pages 042 - 3 * |
| 湖南大学环境工程系, 湖南大学出版社, pages: 46 - 48 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113365283A (en) * | 2020-11-16 | 2021-09-07 | 南京航空航天大学 | Unmanned aerial vehicle ad hoc network channel access control method based on flow prediction |
| CN115032361A (en) * | 2021-03-03 | 2022-09-09 | 中国石油化工股份有限公司 | Method for evaluating organic carbon content of shale oil reservoir based on genetic optimization neural network algorithm |
| CN115511230A (en) * | 2022-11-23 | 2022-12-23 | 国网浙江省电力有限公司宁波供电公司 | Electric energy substitution potential analysis and prediction method |
| CN115511230B (en) * | 2022-11-23 | 2023-04-07 | 国网浙江省电力有限公司宁波供电公司 | Electric energy substitution potential analysis and prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111325325A (en) | Method for predicting electric energy substitution potential based on genetic algorithm and BP neural network combination | |
| Lu et al. | Carbon trading volume and price forecasting in China using multiple machine learning models | |
| Lin et al. | Energy demand in China: Comparison of characteristics between the US and China in rapid urbanization stage | |
| Sun et al. | Solving job shop scheduling problem using genetic algorithm with penalty function | |
| CN112036633B (en) | Optimal scheduling method based on reservoir ecological power generation multi-target medium and long term random scheduling model | |
| Jiao et al. | Clonal selection with immune dominance and anergy based multiobjective optimization | |
| CN112906974A (en) | Load electric quantity and carbon emission prediction and calibration method thereof | |
| CN105404926A (en) | Aluminum electrolytic production technology optimization method based on BP neural network and MBFO algorithm | |
| CN115907070A (en) | Regional carbon emission prediction method based on electric power data | |
| CN105302976A (en) | Aluminum electrolysis production optimization method based on SPEA2 algorithm | |
| CN111047091B (en) | Lasso and RNN-based provincial energy utilization efficiency prediction method | |
| Tong et al. | Natural gas consumption forecasting using an optimized Grey Bernoulli model: The case of the world’s top three natural gas consumers | |
| CN115409259A (en) | Power load probability prediction method | |
| CN111523807B (en) | Electric energy substitution potential analysis method based on time sequence and neural network | |
| Chen et al. | Research on prediction methods of energy consumption data | |
| CN114021819B (en) | Thermal power plant nitrogen oxide content prediction method based on fractional gray delay model | |
| Mu et al. | An improved effective approach for urban air quality forecast | |
| CN115660038A (en) | Multi-stage integrated short-term load prediction based on error factors and improved MOEA/D-SAS | |
| CN115860232A (en) | Steam load prediction method, system, electronic device and medium | |
| Hao et al. | An effective Markov network based EDA for flexible job shop scheduling problems under uncertainty | |
| CN113420464A (en) | Aisle arrangement method considering robustness | |
| Deng et al. | Grey relational analysis and fuzzy neural network method for predicting corrosion rate of marine pipeline | |
| CN115730701B (en) | Load prediction method and system suitable for power dispatching equipment in small energy consumption place | |
| Shu et al. | A Novel EGM (1, 1) Model Based On Kernel And Degree Of Greyness And Its Application On Smog Prediction. | |
| Zhang et al. | Carbon emissions forecasting based on stacking ensemble learning |
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 |