CN114372691A - Electric energy substitution potential estimation method based on holographic perception - Google Patents
Electric energy substitution potential estimation method based on holographic perception Download PDFInfo
- Publication number
- CN114372691A CN114372691A CN202111651702.2A CN202111651702A CN114372691A CN 114372691 A CN114372691 A CN 114372691A CN 202111651702 A CN202111651702 A CN 202111651702A CN 114372691 A CN114372691 A CN 114372691A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy substitution
- substitution
- model
- consumption
- 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 99
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000008447 perception Effects 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 230000006399 behavior Effects 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims abstract description 5
- 230000005611 electricity Effects 0.000 claims abstract description 4
- 238000005265 energy consumption Methods 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 10
- 230000008901 benefit Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000000611 regression analysis Methods 0.000 claims description 8
- 238000011160 research Methods 0.000 claims description 7
- 239000010742 number 1 fuel oil Substances 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 4
- 150000001875 compounds Chemical class 0.000 claims description 3
- RVRCFVVLDHTFFA-UHFFFAOYSA-N heptasodium;tungsten;nonatriacontahydrate Chemical compound O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.[Na+].[Na+].[Na+].[Na+].[Na+].[Na+].[Na+].[W].[W].[W].[W].[W].[W].[W].[W].[W].[W].[W] RVRCFVVLDHTFFA-UHFFFAOYSA-N 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 2
- 239000007789 gas Substances 0.000 description 5
- 230000009467 reduction Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000003034 coal gas Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an electric energy substitution potential estimation method based on holographic perception, which comprises the following steps: step 1, load identification is carried out on electric energy replacing key equipment; step 2, carrying out a load identification result based on the electric energy substitution key equipment in the step 1, and comprehensively analyzing the electricity utilization behavior and the electric energy substitution potential; step 3, according to the comprehensive analysis result of the power utilization behaviors and the electric energy substitution potentials in the step 2, establishing a prediction model by adopting an STIRPAT-ridge regression algorithm to predict the electric energy substitution potentials; step 4, correcting the prediction model established in the step 3; and 5, correcting the predicted value of the electric energy substitution potential based on the electric energy substitution prediction correction model obtained in the step 4, and finishing the evaluation of the electric energy substitution potential. The invention can solve the technical problems of user personalized data acquisition and behavior perception facing electric energy substitution potential analysis.
Description
Technical Field
The invention belongs to the technical field of electric energy substitution, and relates to an electric energy substitution potential estimation method, in particular to an electric energy substitution potential estimation method based on holographic sensing.
Background
The strategy of replacing electric energy mainly means that electric energy is used for replacing conventional terminal energy such as coal, oil, gas and the like, the fuel use efficiency is improved, the pollutant emission is reduced through large-scale centralized conversion, and the effects of improving the terminal energy structure and promoting the environmental protection are achieved.
With the progress of research, a great deal of research on electric energy substitution potential emerges, and a document [1] analyzes the influence on the consumption level of residents from two aspects of consumption expenditure structural change and domestic consumption growth of residents in cities and towns in China by applying a vector autoregressive model, so as to obtain the potential of the consumption level of residents. The literature [2] indicates that the apparent potential of energy conservation and emission reduction is a difference between the energy utilization efficiency, the reasonable energy utilization degree, the emission reduction of atmospheric pollutants and the like in a region and the advanced level, and a Chinese AP-ESER analysis system is constructed by using a DEA method, so that the influence of data precision, data integrity and regional difference on an analysis result is effectively reduced. The technology for reducing emission of greenhouse gases in rural energy is comprehensively analyzed and evaluated in the literature [3], the effect of reducing emission is calculated, and the future potential of reducing emission is estimated.
In general, models for researching potential mostly take regions as objects, but most methods cannot perform differentiation analysis on specific user individuals, and for industrial users, the energy usage habits of the industrial users are different, estimation is simply performed through historical data and induction of users of the same type, and estimation of the user electric energy substitution potential after coal gas oil-electricity multi-scene conversion under different time scales is difficult to perform with high precision. Therefore, although the analysis results of the existing methods have guiding significance, it is difficult to form clear estimation and implementation in the specific case of actual engineering.
Through searching, the patent documents of the prior art which are the same as or similar to the invention are not found.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides an electric energy substitution potential estimation method based on holographic sensing, and can solve the technical problems of user personalized data acquisition and behavior sensing oriented to electric energy substitution potential analysis.
The invention solves the practical problem by adopting the following technical scheme:
a holographic perception-based electric energy substitution potential estimation method comprises the following steps:
step 1, load identification is carried out on electric energy replacing key equipment;
step 2, carrying out a load identification result based on the electric energy substitution key equipment in the step 1, and comprehensively analyzing the electricity utilization behavior and the electric energy substitution potential;
step 3, according to the comprehensive analysis result of the power utilization behaviors and the electric energy substitution potentials in the step 2, establishing a prediction model by adopting an STIRPAT-ridge regression algorithm to predict the electric energy substitution potentials;
step 4, correcting the prediction model established in the step 3;
and 5, correcting the predicted value of the electric energy substitution potential based on the electric energy substitution prediction correction model obtained in the step 4, and finishing the evaluation of the electric energy substitution potential.
Further, the specific steps of step 1 include:
(1) the method comprises the steps that target users are sampled to obtain high-frequency monitoring data and energy consumption historical data, and relevant dimension information in the operation process of various target devices is found out by combining with the mechanism analysis of energy consumption devices;
(2) analyzing to obtain main target energy-using equipment for replacing the electric energy of the large-scale industrial users, and constructing and forming an electric energy replacement key equipment library;
(3) combining the relevant dimension information obtained in the step (1) in the running process of each device with the electric energy substitution key device library obtained in the step (2) to form a key device perception feature library suitable for load monitoring;
(4) and (3) according to the electric energy substitution key equipment library obtained in the step (2) and the key equipment perception feature library obtained in the step (3), completing electric energy substitution key equipment identification through pattern matching.
Moreover, the specific method of the step 2 is as follows:
firstly, modeling a substitution model under multiple scenes such as coal oil gas and the like through the existing research; further carrying out personalized analysis and modeling on the power utilization behavior rule of the user on the basis of the electric energy replacing key equipment identification technology; and combining grey correlation degree analysis, carrying out comprehensive benefit calculation on the electric energy substitution levels under different scenes/models, and dynamically selecting the models under the condition of complex energy consumption of different users according to the calculation result.
Further, the specific steps of step 3 include:
(1) defining electric energy replacing electric quantity as a characteristic value of electric energy replacing potential, and setting a reference year TBThe increase of the electric energy consumption in the t year compared with the reference electric energy consumption is defined as electric energy substitution amount:
wherein S istFor alternative energy, YtActual power consumption of the t year, EtThe total energy consumption of the terminal in the t year;
(2) expanding and transforming the STIRPAT model, and constructing an STIRPAT model expression related to electric energy substitution:
in the formula, S is the terminal electric energy alternative power is the electric energy alternative power, a is the model coefficient, T is the terminal electric energy consumption intensity, Y is the terminal electric energy consumption, E is the usage of certain energy, O is other factors influencing the electric energy alternative power, beta1、β2、β3、β4Coefficients of the influencing factor T, Y, D, O, respectively, e is a random error term of the model;
(3) to determine the relevant parameters by regression analysis, the two sides of (2) were logarithmized to obtain:
LnS=Lnα+β1LnT+β1LnY+β1LnD+β1LnO+Lne (3)
(4) fitting the model of the step (3) by using a ridge regression algorithm:
the method comprises the steps of firstly training a ridge regression model by taking historical data of a target device as a training set sample, and then predicting new data by using the trained model.
Further, the specific steps of step 4 include:
(1) combining wavelet analysis with an artificial neural network, training the wavelet neural network through residual historical data, and dynamically correcting the prediction model result in the step 3, wherein the calculation mode of the residual is as shown in a formula (4);
et=(Yt-1+St)-Yt (4)
wherein, the power consumption of the terminal Y in the t-1 th yeart-1And the substituted quantity S obtained by fittingtThe sum of (a) and (b) is the fitted consumption of the t yearResidual error etTo fit the consumptionThe difference from the actual consumption;
(2) for a given wavelet neural network (the number of neurons in the input layer, hidden layer and output layer is m, N and N respectively), let X be the input vector and X be the output vector1x2…xN]Then its model output can be expressed as:
in the formula (I), the compound is shown in the specification,xkand yiThe kth input, respectively vector X, and the ith output of the output layer; a isjAnd bjRespectively the wavelet basis expansion factor and the translation factor of the jth hidden layer node; w is aj,kAnd wi,jRespectively connecting weights of an input layer node k, a hidden layer node j, the hidden layer node j and an output layer node i; h (x) is a Sigmoid function.
(3) After obtaining the residual history data, the key of the network training process is to determine a set of appropriate weights and wavelet bases so that the following objective function values are minimum:
in the formula,P=(w c)T(ii) a w and c are vectors formed by all weights and wavelet bases in the network respectively; t is tiIs the desired output of the network.
Moreover, the specific method of the step 5 is as follows:
prediction result S of ridge regression analysistResidual error intelligently corrected based on wavelet neural networkIn combination, the prediction of the electric energy substitution amount is realized to obtain a predicted value
The invention has the advantages and beneficial effects that:
1. in order to estimate the electric energy substitution potential for a specific user, the invention firstly solves the problems of user personalized data acquisition and behavior perception facing electric energy substitution potential analysis on the basis of a load identification technology. Furthermore, by flexible application of machine learning algorithms such as gray level correlation, ridge regression analysis, wavelet neural network and the like, multi-scene-oriented random time scale electric energy substitution potential calculation is realized, so that application of electric energy substitution in industrial users is realized.
2. Aiming at a primary target user-a large industrial user substituted by electric energy, the method carries out targeted algorithm design by combining a research paradigm of mode identification in an artificial intelligence technology so as to quickly, efficiently and accurately obtain the power utilization information of target equipment and carry out personalized analysis on the power utilization behavior rule of the user; then, analyzing the electric energy substitution potential based on the multi-scene electric energy substitution equivalent model and the user energy consumption behavior model, and dynamically selecting the model under the condition of different user complex energy consumption; and finally, accurately predicting the electric energy substitution amount through technologies such as regression analysis and wavelet neural network, realizing comprehensive evaluation of the electric energy substitution potential of the user under multiple time spans, and providing support for subsequent benefit analysis and accounting.
3. The invention provides an electric energy substitution potential estimation method based on holographic sensing, which aims to solve the problem of accurate evaluation of electric energy substitution potential of specific users, can further promote popularization and application of electric energy substitution in the industrial field, and helps coal oil gas multi-type energy electric energy substitution units to greatly save capacity investment cost. The invention can provide a generalizable automatic personalized estimation method for electric energy substitution, improve the service efficiency of electric power enterprises, and provide a reference for the improvement and upgrading of energy structure in China, thereby greatly improving the equipment utilization rate of an electric energy substitution technical scene.
Drawings
FIG. 1 is a flow chart of the holographic sensing-based electric energy substitution potential estimation method of the present invention;
FIG. 2 is a flow chart of a method for identifying the operation status of a user's key device according to the present invention;
FIG. 3 is a flow chart of the power substitution long-term and short-term potential estimation of the present invention.
Detailed Description
The embodiments of the invention will be described in further detail below with reference to the accompanying drawings:
a method for estimating electric energy substitution potential based on holographic perception is shown in FIG. 1, and comprises the following steps:
step 1, load identification is carried out on electric energy replacing key equipment;
as shown in fig. 2, the specific steps of step 1 include:
1-1) sampling target users to obtain high-frequency monitoring data and energy consumption historical data, and finding out relevant dimension information in the operation process of various target devices by combining with mechanism analysis of energy consumption devices;
1-2) analyzing to obtain main target energy-using equipment for replacing the electric energy of the large-scale industrial users, and constructing and forming an electric energy replacement key equipment library;
1-3) combining the relevant dimension information obtained in the step 1-1) in the running process of each device with the electric energy substitution key device library obtained in the step 1-2) to form a key device perception feature library suitable for load monitoring;
1-4) according to the electric energy substitution key equipment library obtained in the step 1-2) and the key equipment perception feature library obtained in the step 1-3), finishing electric energy substitution key equipment identification through pattern matching and other related technologies.
Step 2, carrying out a load identification result based on the electric energy substitution key equipment in the step 1, and comprehensively analyzing the electricity utilization behavior and the electric energy substitution potential;
the specific method of the step 2 comprises the following steps:
firstly, modeling a substitution model under multiple scenes such as coal oil gas and the like through the existing research; further carrying out personalized analysis and modeling on the power utilization behavior rule of the user on the basis of the electric energy replacing key equipment identification technology; and combining grey correlation degree analysis, carrying out comprehensive benefit calculation on the electric energy substitution levels under different scenes/models, and dynamically selecting the models under the condition of complex energy consumption of different users according to the calculation result.
Step 3, according to the comprehensive analysis result of the power utilization behaviors and the electric energy substitution potentials in the step 2, establishing a prediction model by adopting an STIRPAT-ridge regression algorithm to predict the electric energy substitution potentials;
the specific steps of the step 3 comprise:
(1) in order to realize quantitative calculation of the electric energy substitution potential, the electric energy substitution electric quantity is defined as a characteristic value of the electric energy substitution potential, and a reference year T is setBThe increase of the electric energy consumption in the t year compared with the reference electric energy consumption is defined as electric energy substitution amount:
wherein S istFor alternative energy, YtActual power consumption of the t year, EtThe total energy consumption of the terminal in the t year;
(2) the invention expands and reforms the STIRPAT model to construct an STIRPAT model expression related to electric energy substitution, wherein the STIRPAT model is a multi-independent variable nonlinear model, and polynomial parameters are time-varying:
in the formula, S is the terminal electric energy alternative power is the electric energy alternative power, a is the model coefficient, T is the terminal electric energy consumption intensity, Y is the terminal electric energy consumption, E is the usage of certain energy, O is other factors influencing the electric energy alternative power, beta1、β2、β3、β4Respectively, the coefficients of the influencing factor T, Y, D, O, e being the random error term of the model.
(3) To determine the relevant parameters by regression analysis, the two sides of (2) were logarithmized to obtain:
LnS=Lnα+β1LnT+β1LnY+β1LnD+β1LnO+Lne (3)
(4) fitting the model of the step (3) by using a ridge regression algorithm:
the method comprises the steps of firstly training a ridge regression model by taking historical data of a target device as a training set sample, and then predicting new data by using the trained model.
Step 4, correcting the prediction model established in the step 3, further improving the prediction precision of the algorithm, and avoiding precision reduction caused by long-term prediction;
as shown in fig. 3, the specific steps of step 4 include:
(1) combining wavelet analysis with an artificial neural network, training the wavelet neural network through residual historical data, and dynamically correcting the prediction model result in the step 3, wherein the calculation mode of the residual is as shown in a formula (4);
et=(Yt-1+St)-Yt (4)
wherein, the power consumption of the terminal Y in the t-1 th yeart-1And the substituted quantity S obtained by fittingtThe sum of (a) and (b) is the fitted consumption of the t yearResidual error etTo fit the consumptionDifference from actual consumption:
due to residual sequence etThe method has strong randomness and irregular fluctuation, so that the change trend of the traditional prediction model is difficult to accurately depict by adopting the traditional prediction model. The wavelet analysis has good time-frequency localization property and high convergence speed, and the residual sequence e can be combined with the self-adaption and self-learning capabilities of the artificial neural networktThe accuracy of the prediction result is higher.
Wavelet neural network using wavelet basis function fi(x) (i ═ 1,2, …, k) replaces the activation function of the hidden layer of the traditional BP neural network. The combination ensures that the artificial neural network model not only keeps the advantages of the BP neural network, but also optimizes the weight and the threshold of the BP neural network by utilizing the advantage that the wavelet transformation has the capability of extracting local information by amplifying signals, thereby overcoming the defect that the BP network is easily influenced by local extremum to cause lower precision of the forecast result.
(2) For a given wavelet neural network (the number of neurons in the input layer, hidden layer and output layer is m, N and N respectively), let X be the input vector and X be the output vector1x2…xN]Then its model output can be expressed as:
in the formula (I), the compound is shown in the specification,xkand yiThe kth input, respectively vector X, and the ith output of the output layer; a isjAnd bjRespectively the wavelet basis expansion factor and the translation factor of the jth hidden layer node; w is aj,kAnd wi,jRespectively connecting weights of an input layer node k, a hidden layer node j, the hidden layer node j and an output layer node i; h (x) is a Sigmoid function.
(3) After obtaining the residual history data, the key of the network training process is to determine a set of appropriate weights and wavelet bases so that the following objective function values are minimum:
in the formula, P ═ w cT(ii) a w and c are vectors formed by all weights and wavelet bases in the network respectively; t is tiIs the desired output of the network.
Using wavelet neural network to correct residual error etSelf-learning is carried out to obtain an output residual sequenceAnd repeatedly training the network by taking the original residual sequence data as expected output until the training error meets the precision requirement, thereby ensuring the network prediction precision and generalization capability. Dynamically correcting the result of the prediction model, constructing an electric energy substitution intelligent correction model which can adapt to different time scales, and intelligently correcting the electric energy substitution predicted value by the wavelet neural network obtained by training so as to improve the prediction precision.
Step 5, correcting the predicted value of the electric energy substitution potential based on the electric energy substitution prediction correction model obtained in the step 4, and finishing electric energy substitution potential evaluation;
the specific method of the step 5 comprises the following steps:
prediction result S of ridge regression analysistResidual error intelligently corrected based on wavelet neural networkIn combination, the prediction of the electric energy substitution amount is realized to obtain a predicted value
The working principle of the invention is as follows:
the invention discloses an electric energy substitution latent estimation method based on holographic perception, which comprises the following steps: based on the high-frequency monitoring data and the energy consumption historical data of the target user, the mechanism analysis of the energy consumption equipment is combined, and the relevant dimension information of various target equipment in the operation process is found out; the method comprises the steps of finding out main target energy-using equipment for replacing the electric energy of large-scale industrial users through investigation and analysis, constructing and forming an electric energy replacement key equipment library, and forming a key equipment perception feature library suitable for load monitoring by combining relevant dimension information in the operation process of each equipment; the identification of the electric energy substitution key equipment is completed by combining an electric energy substitution key equipment library and a key equipment perception characteristic library and by using a mode matching and other related technologies; firstly, modeling a substitution model under multiple scenes such as coal oil gas and the like through the existing research; further carrying out personalized analysis and modeling on the power utilization behavior rule of the user on the basis of the electric energy replacing key equipment identification technology; and combining grey correlation degree analysis, carrying out comprehensive benefit calculation on the electric energy substitution levels under different scenes/models, and dynamically selecting the models under the condition of complex energy consumption of different users according to the calculation result. Predicting the electric energy substitution level by adopting an STIRPAT model and a ridge regression algorithm; combining wavelet analysis with an artificial neural network, training the wavelet neural network through residual historical data, dynamically correcting a prediction model result, and finishing electric energy substitution potential estimation.
It should be emphasized that the examples described herein are illustrative and not restrictive, and thus the present invention includes, but is not limited to, those examples described in this detailed description, as well as other embodiments that can be derived from the teachings of the present invention by those skilled in the art and that are within the scope of the present invention.
Claims (6)
1. A method for estimating electric energy substitution potential based on holographic perception is characterized by comprising the following steps: the method comprises the following steps:
step 1, load identification is carried out on electric energy replacing key equipment;
step 2, carrying out a load identification result based on the electric energy substitution key equipment in the step 1, and comprehensively analyzing the electricity utilization behavior and the electric energy substitution potential;
step 3, according to the comprehensive analysis result of the power utilization behaviors and the electric energy substitution potentials in the step 2, establishing a prediction model by adopting an STIRPAT-ridge regression algorithm to predict the electric energy substitution potentials;
step 4, correcting the prediction model established in the step 3;
and 5, correcting the predicted value of the electric energy substitution potential based on the electric energy substitution prediction correction model obtained in the step 4, and finishing the evaluation of the electric energy substitution potential.
2. The method for estimating electric energy substitution potential based on holographic perception according to claim 1, wherein: the specific steps of the step 1 comprise:
(1) the method comprises the steps that target users are sampled to obtain high-frequency monitoring data and energy consumption historical data, and relevant dimension information in the operation process of various target devices is found out by combining with the mechanism analysis of energy consumption devices;
(2) analyzing to obtain main target energy-using equipment for replacing the electric energy of the large-scale industrial users, and constructing and forming an electric energy replacement key equipment library;
(3) combining the relevant dimension information obtained in the step (1) in the running process of each device with the electric energy substitution key device library obtained in the step (2) to form a key device perception feature library suitable for load monitoring;
(4) and (3) according to the electric energy substitution key equipment library obtained in the step (2) and the key equipment perception feature library obtained in the step (3), completing electric energy substitution key equipment identification through pattern matching.
3. The method for estimating electric energy substitution potential based on holographic perception according to claim 1, wherein: the specific method of the step 2 comprises the following steps:
firstly, modeling a substitution model under multiple scenes such as coal oil gas and the like through the existing research; further carrying out personalized analysis and modeling on the power utilization behavior rule of the user on the basis of the electric energy replacing key equipment identification technology; and combining grey correlation degree analysis, carrying out comprehensive benefit calculation on the electric energy substitution levels under different scenes/models, and dynamically selecting the models under the condition of complex energy consumption of different users according to the calculation result.
4. The method for estimating electric energy substitution potential based on holographic perception according to claim 1, wherein: the specific steps of the step 3 comprise:
(1) defining electric energy replacing electric quantity as a characteristic value of electric energy replacing potential, and setting a reference year TBThe increase of the electric energy consumption in the t year compared with the reference electric energy consumption is defined as electric energy substitution amount:
wherein S istFor alternative energy, YtActual power consumption of the t year, EtThe total energy consumption of the terminal in the t year;
(2) expanding and transforming the STIRPAT model, and constructing an STIRPAT model expression related to electric energy substitution:
in the formula, S is the terminal electric energy alternative power is the electric energy alternative power, a is the model coefficient, T is the terminal electric energy consumption intensity, Y is the terminal electric energy consumption, E is the usage of certain energy, O is other factors influencing the electric energy alternative power, beta1、β2、β3、β4Coefficients of the influencing factor T, Y, D, O, respectively, e is a random error term of the model;
(3) to determine the relevant parameters by regression analysis, the two sides of (2) were logarithmized to obtain:
LnS=Lnα+β1LnT+β1LnY+β1LnD+β1LnO+Lne (3)
(4) fitting the model of the step (3) by using a ridge regression algorithm:
the method comprises the steps of firstly training a ridge regression model by taking historical data of a target device as a training set sample, and then predicting new data by using the trained model.
5. The method for estimating electric energy substitution potential based on holographic perception according to claim 1, wherein: the specific steps of the step 4 comprise:
(1) combining wavelet analysis with an artificial neural network, training the wavelet neural network through residual historical data, and dynamically correcting the prediction model result in the step 3, wherein the calculation mode of the residual is as shown in a formula (4);
et=(Yt-1+St)-Yt (4)
wherein, the power consumption of the terminal Y in the t-1 th yeart-1And the substituted quantity S obtained by fittingtThe sum of (a) and (b) is the fitted consumption of the t yearResidual error etTo fit the consumptionThe difference from the actual consumption;
(2) for a given wavelet neural network (the number of neurons in the input layer, hidden layer and output layer is m, N and N respectively), let X be the input vector and X be the output vector1x2…xN]Then its model output can be expressed as:
in the formula (I), the compound is shown in the specification,xkand yiThe kth input, respectively vector X, and the ith output of the output layer; a isjAnd bjRespectively the wavelet basis expansion factor and the translation factor of the jth hidden layer node; w is aj,kAnd wi,jRespectively connecting weights of an input layer node k, a hidden layer node j, the hidden layer node j and an output layer node i; h (x) is a Sigmoid function.
(3) After obtaining the residual history data, the key of the network training process is to determine a set of appropriate weights and wavelet bases so that the following objective function values are minimum:
in the formula, P ═ w cT(ii) a w and c are vectors formed by all weights and wavelet bases in the network respectively; t is tiIs the desired output of the network.
6. The method for estimating electric energy substitution potential based on holographic perception according to claim 1, wherein: the specific method of the step 5 comprises the following steps:
prediction result S of ridge regression analysistResidual error intelligently corrected based on wavelet neural networkIn combination, the prediction of the electric energy substitution amount is realized to obtain a predicted value
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111651702.2A CN114372691A (en) | 2021-12-29 | 2021-12-29 | Electric energy substitution potential estimation method based on holographic perception |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111651702.2A CN114372691A (en) | 2021-12-29 | 2021-12-29 | Electric energy substitution potential estimation method based on holographic perception |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114372691A true CN114372691A (en) | 2022-04-19 |
Family
ID=81142400
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111651702.2A Pending CN114372691A (en) | 2021-12-29 | 2021-12-29 | Electric energy substitution potential estimation method based on holographic perception |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114372691A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103295075A (en) * | 2013-04-01 | 2013-09-11 | 沈阳航空航天大学 | Ultra-short-term power load forecasting and early warning method |
CN107730041A (en) * | 2017-10-12 | 2018-02-23 | 东华大学 | Short-Term Load Forecasting Method based on improved genetic wavelet neural network |
CN108062598A (en) * | 2017-12-11 | 2018-05-22 | 天津天大求实电力新技术股份有限公司 | New situation load potential prediction method under multi-scenario |
CN109426889A (en) * | 2017-09-01 | 2019-03-05 | 南京理工大学 | Short-term load forecasting method based on KPCA in conjunction with improvement neural network |
CN111832785A (en) * | 2019-04-23 | 2020-10-27 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting electric energy substitution potential |
CN112633924A (en) * | 2020-12-21 | 2021-04-09 | 国网浙江省电力有限公司嘉兴供电公司 | Cell electric energy substitution demand analysis method based on load decomposition |
-
2021
- 2021-12-29 CN CN202111651702.2A patent/CN114372691A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103295075A (en) * | 2013-04-01 | 2013-09-11 | 沈阳航空航天大学 | Ultra-short-term power load forecasting and early warning method |
CN109426889A (en) * | 2017-09-01 | 2019-03-05 | 南京理工大学 | Short-term load forecasting method based on KPCA in conjunction with improvement neural network |
CN107730041A (en) * | 2017-10-12 | 2018-02-23 | 东华大学 | Short-Term Load Forecasting Method based on improved genetic wavelet neural network |
CN108062598A (en) * | 2017-12-11 | 2018-05-22 | 天津天大求实电力新技术股份有限公司 | New situation load potential prediction method under multi-scenario |
CN111832785A (en) * | 2019-04-23 | 2020-10-27 | 国网浙江省电力有限公司电力科学研究院 | Method and system for predicting electric energy substitution potential |
CN112633924A (en) * | 2020-12-21 | 2021-04-09 | 国网浙江省电力有限公司嘉兴供电公司 | Cell electric energy substitution demand analysis method based on load decomposition |
Non-Patent Citations (3)
Title |
---|
""基于STIRPAT- 岭回归的电能替代潜力分析方法"", 《供用电》 * |
孙毅 等: ""多情景下的电能替代潜力分析"", 《电网技术》 * |
毛雪娇: ""考虑电能替代潜力的饱和负荷预测方法研究"", 《中国优秀硕士学位论文全文数据库 (月刊) 2020 年 第06期》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
CN110705743B (en) | New energy consumption electric quantity prediction method based on long-term and short-term memory neural network | |
Song et al. | Hourly heat load prediction model based on temporal convolutional neural network | |
CN111428926B (en) | Regional power load prediction method considering meteorological factors | |
CN112990500B (en) | Transformer area line loss analysis method and system based on improved weighted gray correlation analysis | |
CN111079989A (en) | Water supply company water supply amount prediction device based on DWT-PCA-LSTM | |
CN110659779B (en) | Power distribution system network loss prediction method based on long-term and short-term memory network | |
Liu et al. | Heating load forecasting for combined heat and power plants via strand-based LSTM | |
CN112381673B (en) | Park electricity utilization information analysis method and device based on digital twin | |
CN104036328A (en) | Self-adaptive wind power prediction system and prediction method | |
Song et al. | An indoor temperature prediction framework based on hierarchical attention gated recurrent unit model for energy efficient buildings | |
CN112418495A (en) | Building energy consumption prediction method based on longicorn stigma optimization algorithm and neural network | |
CN115099511A (en) | Photovoltaic power probability estimation method and system based on optimized copula | |
Xue et al. | Prediction of natural gas consumption for city-level DHS based on attention GRU: A case study for a northern chinese city | |
CN114119273A (en) | Park comprehensive energy system non-invasive load decomposition method and system | |
CN113762591B (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM countermeasure learning | |
CN114372691A (en) | Electric energy substitution potential estimation method based on holographic perception | |
Kumar et al. | Forecasting indoor temperature for smart buildings with ARIMA, SARIMAX, and LSTM: A fusion approach | |
CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks | |
CN117634678A (en) | Low-carbon park carbon emission prediction method based on actual operation scene | |
CN116451873B (en) | Wind power generation power prediction method and system based on multi-scale double space-time network area | |
Wang et al. | Cloud computing and extreme learning machine for a distributed energy consumption forecasting in equipment-manufacturing enterprises | |
CN116561569A (en) | Industrial power load identification method based on EO feature selection and AdaBoost algorithm | |
CN115511230A (en) | Electric energy substitution potential analysis and prediction method | |
CN111626465A (en) | New energy power short-term interval prediction method and system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220419 |