CN112016815A - User side comprehensive energy efficiency evaluation method based on neural network - Google Patents
User side comprehensive energy efficiency evaluation method based on neural network Download PDFInfo
- Publication number
- CN112016815A CN112016815A CN202010798317.XA CN202010798317A CN112016815A CN 112016815 A CN112016815 A CN 112016815A CN 202010798317 A CN202010798317 A CN 202010798317A CN 112016815 A CN112016815 A CN 112016815A
- Authority
- CN
- China
- Prior art keywords
- energy efficiency
- index
- user
- neural network
- comprehensive energy
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 59
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000013210 evaluation model Methods 0.000 claims abstract description 16
- 238000004519 manufacturing process Methods 0.000 claims description 21
- 230000008901 benefit Effects 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 11
- 238000005265 energy consumption Methods 0.000 claims description 10
- 210000002569 neuron Anatomy 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004378 air conditioning Methods 0.000 claims description 3
- 239000003344 environmental pollutant Substances 0.000 claims description 3
- 238000003912 environmental pollution Methods 0.000 claims description 3
- 239000000446 fuel Substances 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 231100000719 pollutant Toxicity 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000004044 response Effects 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
Abstract
The invention discloses a user side comprehensive energy efficiency evaluation method based on a neural network, which comprises the steps of constructing a first-level index of a user and a second-level index corresponding to the first-level index, and using the second-level index and the first-level index score of each known user as a training sample; inputting the training sample into a comprehensive energy efficiency evaluation model based on a neural network for training, and determining a network structure and parameters of the neural network; and inputting the secondary indexes of the user to be evaluated into the trained comprehensive energy efficiency evaluation model, and outputting the primary index score of the user to be evaluated. According to the user-side comprehensive energy efficiency evaluation method based on the neural network, provided by the invention, a training sample is obtained by combining subjective weighting with actual conditions, an energy efficiency evaluation model is established by using the neural network method, index weight is continuously iterated and optimized, and energy efficiency score is obtained by calculation. The efficiency evaluation efficiency is greatly improved, and the similar objects are quickly evaluated.
Description
Technical Field
The invention relates to a user side comprehensive energy efficiency evaluation method based on a neural network, and belongs to the technical field of power utilization service evaluation.
Background
With the continuous promotion of the industrialization process, the demand and the consumption of energy are increased sharply, and the energy supply situation is severe. In the key period of energy transformation in China, green development must be continuously promoted, and a clean low-carbon, safe and efficient energy system is established. However, many energy-consuming enterprises neglect the energy consumption problem in order to seek economic benefits, and form a situation of high emission and high pollution.
In order to solve the common phenomena of energy waste, unreasonable energy utilization and low-efficiency energy utilization of users, energy efficiency evaluation and energy-saving modification of related enterprises on the user side are urgently needed. However, an evaluation system capable of reflecting enterprise energy utilization characteristics is lacked at present, and comprehensive and accurate evaluation cannot be provided for various user side energy utilization equipment, user side energy production, demand response resources, production technologies, environments, user behaviors and the like. The energy efficiency evaluation system can mine the energy data value of the user and provide scientific basis for the user to perform energy structure optimization, energy-saving transformation, participation in demand response and the like, so that the energy utilization efficiency of the user is improved, and the energy cost of the user is reduced.
In the aspect of user-side energy efficiency management, energy efficiency evaluation is a multi-index comprehensive evaluation problem, and the existing evaluation method is lack of objectivity and is combined with actual conditions. The energy efficiency evaluation index system is complex, a plurality of factors influencing the energy efficiency of the user side exist, and the variable types of the factors are different. At present, no complete comprehensive energy efficiency evaluation system and evaluation method are available for evaluating the energy level of users.
Disclosure of Invention
The purpose is as follows: in order to overcome the defects in the prior art, the invention provides a user side comprehensive energy efficiency evaluation method based on a neural network, which comprises the steps of constructing a user side comprehensive energy efficiency evaluation index system, establishing an energy efficiency evaluation model based on the neural network method, determining index weight by utilizing the self-adaptability of the neural network method, avoiding the interference of human factors and improving the energy efficiency evaluation efficiency.
The technical scheme is as follows: in order to solve the technical problems, the technical scheme adopted by the invention is as follows:
the invention provides a user side comprehensive energy efficiency evaluation method based on a neural network,
according to a first aspect of the present invention, a user-side comprehensive energy efficiency evaluation method based on a neural network is provided, including:
acquiring energy efficiency index data of a user to be evaluated, wherein the energy efficiency index data are each secondary energy efficiency index data corresponding to each primary energy efficiency index in a preset index system;
inputting the secondary energy efficiency index data of the user to be evaluated into a pre-trained comprehensive energy efficiency evaluation model to obtain a primary energy efficiency index evaluation result of the user to be evaluated, which is output by the comprehensive energy efficiency evaluation model;
the pre-trained comprehensive energy efficiency evaluation model adopts a neural network, the neural network takes secondary energy efficiency index data as input, takes each primary energy efficiency index evaluation result corresponding to a secondary energy efficiency index as output, and training samples are known primary energy efficiency index evaluation results and corresponding secondary energy efficiency index data.
Preferably, the primary energy efficiency index at least comprises one of economic benefit, electric energy quality, demand side management, production efficiency and environmental index.
As a preferred scheme, the secondary energy efficiency index of the economic benefit index at least comprises one of investment cost, operation cost and operation and maintenance cost;
the secondary energy efficiency index of the power quality index at least comprises one of voltage deviation, power deviation, load rate, grid frequency deviation, three-phase unbalance rate and harmonic distortion rate;
the secondary energy efficiency index of the demand side management index at least comprises one of new energy equipment energy efficiency, conveying efficiency, lighting system energy efficiency, air conditioning system energy efficiency, power consumption peak-valley time period and energy consumption behavior analysis;
the secondary energy efficiency index of the production efficiency index at least comprises one of output value total, unit output value energy efficiency, production system energy efficiency and energy utilization equipment energy efficiency;
the secondary energy efficiency index of the environmental index at least comprises one of fuel consumption, pollutant emission and electromagnetic environmental pollution.
As a preferred scheme, the first-level energy efficiency index evaluation result is a first-level energy efficiency index score, the first-level energy efficiency index score in the training sample is obtained by expert assignment scoring, and the scoring standard is as follows:
for the economic benefit index, scoring by taking whether the loss and the profit amount are as reference;
for the power quality index, judging the power quality as a reference score according to whether the detected power parameter curve is abnormally fluctuated, abnormal times and frequency;
scoring the demand side management indexes by taking whether the demand side management indexes participate in peak clipping and valley filling or not and whether the demand side management indexes participate in clean energy consumption actively or not as reference;
for the production efficiency index, the production value and energy consumption are taken as data basis and are used as reference scoring;
and as for the environmental index, scoring by taking the environmental index which is in accordance with the national regulation as a reference.
As a preferred scheme, the method further comprises the step of carrying out data preprocessing on the secondary energy efficiency index data to be input into the comprehensive energy efficiency evaluation model, wherein the data preprocessing comprises deleting abnormal values and/or data normalization.
As a preferred scheme, the number of neurons in an input layer of the neural network is the number of secondary energy efficiency indexes, and the number of neurons in an output layer is the number of primary energy efficiency indexes.
As a preferred scheme, the neural network training comprises initializing a network, inputting a training sample, setting network parameters, adjusting a weight and a threshold, calculating an error, training until the error output by the network is reduced to a minimum error threshold or reaches the maximum iteration number, and otherwise, updating the weight and continuing the training.
As a preferred scheme, the first-level energy efficiency index evaluation result is a first-level energy efficiency index score; the method further comprises the following steps:
calculating the average value of the primary energy efficiency index scores of the users as the comprehensive energy efficiency score of the users;
determining a comprehensive energy efficiency grade of a user to be evaluated according to the comprehensive energy efficiency grade of the user and a preset energy efficiency grade determination rule;
the comprehensive energy efficiency grade comprises a plurality of grades corresponding to a plurality of comprehensive energy efficiency grading ranges; the preset energy efficiency grade determination rule is as follows: and determining a corresponding comprehensive energy efficiency grade according to the comprehensive energy efficiency grading range to which the user comprehensive energy efficiency grade belongs.
As a preferred scheme, the step of dividing the comprehensive energy efficiency scoring range corresponding to each level in the comprehensive energy efficiency levels comprises the following steps:
sorting the comprehensive energy efficiency scores corresponding to the plurality of users from large to small;
sequentially segmenting the sorted user comprehensive energy efficiency scoring sequence according to a proportional threshold, wherein each segment corresponds to one comprehensive energy efficiency grade, and the comprehensive energy efficiency grades corresponding to the segments sequentially represent that the user energy efficiency level is from high to low according to the sequence of the comprehensive energy efficiency scoring sequence from front to back;
and the numerical value between the minimum value and the maximum value of the user comprehensive energy efficiency score in each segment is the score range corresponding to the energy efficiency grade.
A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method according to the first aspect of the invention.
Has the advantages that: according to the user-side comprehensive energy efficiency evaluation method based on the neural network, provided by the invention, a training sample is obtained by combining subjective weighting with actual conditions, an energy efficiency evaluation model is established by using the neural network method, index weight is continuously iterated and optimized, and energy efficiency score is obtained by calculation. The weight of the evaluation index is determined by utilizing the neural network, so that the influence of personal subjective viewpoints on the artificial determination of the weight is avoided, and the situation that the actual situation is not considered due to the fact that the mathematical method is completely relied on is avoided. The neural network can determine the connection weight, namely the index weight, through iterative training, has strong learning capability and self-adaption capability, has strong nonlinear processing capability, improves the accuracy of energy efficiency evaluation, determines the weight after training, and then directly inputs data of a user to be evaluated, so that the efficiency evaluation efficiency is greatly improved, and the similar objects are quickly evaluated.
Drawings
Fig. 1 shows a general flow of the user-side comprehensive energy efficiency evaluation method.
Fig. 2 shows a comprehensive energy efficiency evaluation index system.
Detailed Description
The present invention will be further described with reference to the following examples.
As shown in fig. 1, a user-side comprehensive energy efficiency evaluation method based on a neural network is described in detail as follows.
(1) Constructing a comprehensive energy efficiency evaluation index system;
and constructing a comprehensive energy efficiency evaluation index system of 1 score, 5 indexes and 22 characteristics. By analyzing energy data, equipment data, operation data, electric energy data, energy efficiency data and environment data of a user side, 5 indexes of economic benefit, electric energy quality, demand side management, production efficiency and environment index are set as first-level indexes, and relevant characteristics influencing the result of the first-level indexes are screened out to serve as second-level indexes. The secondary indexes of the economic benefit comprise investment cost, operation cost and operation and maintenance cost; the secondary indexes of the electric energy quality comprise voltage deviation, power deviation, load rate, grid frequency deviation, three-phase unbalance rate and harmonic distortion rate; the secondary indexes of demand side management comprise new energy equipment energy efficiency, conveying efficiency, lighting system energy efficiency, air conditioning system energy efficiency, power consumption peak-valley time period and energy consumption behavior analysis; the secondary indexes of the production efficiency comprise yield total, unit yield energy efficiency, production system energy efficiency and energy utilization equipment energy efficiency; secondary indicators of the environmental index include fuel consumption, pollutant emissions, electromagnetic environmental pollution. The comprehensive energy efficiency evaluation index system is shown in fig. 2.
(2) Obtaining a first-level index score through expert assignment;
the evaluation capability and the evaluation quality of the neural network are closely related to a training sample set, because no evaluation result sample is accumulated at present, the energy efficiency evaluation problem can be comprehensively evaluated only by subjective evaluation of at least experts during system building, weighting and scoring in the traditional evaluation process, and more reasonable evaluation results can be obtained by introducing expert evaluation into the objective mathematical model method. Therefore, the method scores the existing samples by using an expert assignment method.
And scoring the primary indexes of the users by an expert valuation method to obtain primary index scores, wherein the training sample set comprises the secondary indexes of the users and the primary index scores of the users. The first-level index score can be obtained by combining the multidimensional actual condition of the first-level index of the existing sample data to carry out expert assignment score, and the main method is as follows: for economic benefits, scoring by taking whether loss and profit amount are used as references; for the power quality, judging the power quality as a reference score according to whether the detected power parameter curve fluctuates abnormally, abnormal times and frequency; for demand side management, scoring is carried out by taking whether to participate in peak clipping and valley filling or not and whether to participate in clean energy consumption actively or not as a reference; for the production efficiency, scoring by taking the output value energy consumption as a data base; and as for the environmental index, scoring is carried out by taking the environmental index which is in accordance with the national regulation as a reference. And after scoring, taking the average value of all the primary index scores of the user as the comprehensive energy efficiency score of the user.
(3) Comprehensive energy efficiency scoring grading
In order to better evaluate energy efficiency, the comprehensive energy efficiency score needs to be divided into a range and a grade. And dividing the comprehensive energy efficiency score into 5 grades A-E, wherein the 5 grades A-E represent that the energy efficiency level of the user is from high to low. Sorting all sample users from large to small according to the comprehensive energy efficiency scores, dividing the sample users according to the proportion of 20 percent, wherein [ min, max ] between the minimum value and the maximum value of the first 20 percent scores is the score range of the grade A, and the rest is analogized.
(4) Energy efficiency evaluation model based on neural network
And constructing a comprehensive energy efficiency evaluation model based on the neural network, dividing the training sample into training data and testing data, determining the network structure and parameters of the neural network model, and performing a large number of experiments.
1) And (4) preprocessing data. Firstly, the numerical values of 22 characteristics of the secondary indexes of each user are calculated, abnormal values are deleted, data are normalized, the data are processed to form an input matrix meeting requirements, and 5 primary index scores form an expected output matrix. In order to eliminate the influence of different dimensions among the data, the data needs to be normalized to be in the same order of magnitude, so that the data is convenient to process and analyze. By adopting min-max normalization method, usingCalculating by a formula, wherein max is the maximum value in the data, min is the minimum value in the data, and finally mapping the result value to 0,1]In the meantime.
2) Network structures and parameters of the neural network model are determined. And (3) carrying out neural network modeling by taking the input parameters as secondary indexes of the comprehensive energy efficiency assessment index system, taking the number of neurons in the input layer as the number of the secondary indexes, taking the output parameters as the score of the primary indexes and taking the number of neurons in the output layer as the number of the primary indexes.
3) And determining the number of neurons in the hidden layer, and determining the structural parameters of the neural network model through a parameter sensitivity experiment. There is no ideal analytic formula for determining the reasonable number of hidden layer nodes. The common practice is to choose the number of network hidden layer nodes according to a trial and error method.
4) Training a neural network model, wherein the network training mainly comprises initializing a network, inputting a training sample, setting network parameters, adjusting a weight and a threshold, calculating errors, and training until the error output by the network is reduced to a minimum error threshold or reaches the maximum iteration number, otherwise, updating the weight and continuing training.
5) And calculating the energy efficiency score by using a neural network, inputting the second-level index normalization processing of the test sample, calculating a first-level index value by using the trained network, performing inverse normalization processing on the network output value, and comparing the network output value with the first-level index score scored by the expert to verify the accuracy of the model.
(5) Obtaining a first-level index score by using a trained model
And preprocessing the secondary indexes of the user to be evaluated, inputting the preprocessed secondary indexes into the trained model, outputting the primary index score of the user to be evaluated, and calculating the average value of the primary index scores to obtain the comprehensive energy efficiency score of the user to be evaluated.
(6) Obtaining user energy efficiency level according to comprehensive energy efficiency score
And (4) corresponding to the user grade obtained in the step (3) according to the comprehensive energy efficiency score, and obtaining a corresponding user energy efficiency level according to the user grade. The score of the first-level index is also very important, and a targeted energy-saving optimization scheme and a demand response strategy can be provided for the first-level index. For example, for the demand side response, if the demand side management score output by the model is higher, the user is a good-quality user participating in the demand side response; for the production efficiency, if the production efficiency score output by the model is low, the user production process has a large improvement space, energy efficiency analysis can be performed on energy utilization equipment and production equipment, and the equipment energy efficiency is improved.
Example 1:
in order to comprehensively evaluate the energy efficiency condition of a user and solve the defects of the existing evaluation technology, the invention aims to provide a user side comprehensive energy efficiency evaluation method based on a neural network. The main flow chart is shown in fig. 1, which comprises the following steps:
(1) constructing a comprehensive energy efficiency evaluation index system of 1 score, 5 indexes and 22 characteristics, setting 5 indexes of economic benefit, electric energy quality, demand side management, production efficiency and environmental index as primary indexes, and screening out related 22 characteristics influencing the primary index result as secondary indexes;
(2) performing expert assignment to obtain a first-level index score, performing expert assignment scoring on the first-level index by combining the actual condition of the existing sample data, and calculating the average of the first-level index score to obtain a comprehensive energy efficiency score;
(3) and dividing the energy efficiency score into 5 grades A-E, representing that the energy efficiency level is from high to low, sequencing all samples, dividing the samples according to the proportion of 20 percent, wherein the first 20 percent score [ min, max ] is the score range of the grade A, and the rest is analogized.
(4) Constructing a comprehensive energy efficiency evaluation model based on a neural network, taking secondary index data as input, taking primary index score as expected output, and performing model training;
(5) and inputting the secondary indexes of the user to be evaluated into the trained model, outputting a primary index score, and calculating the average value of the primary index score to be the comprehensive energy efficiency score.
(6) And obtaining a user grade according to the comprehensive energy efficiency score, obtaining a user energy efficiency level according to the user grade, and obtaining corresponding energy efficiency management and energy-saving suggestions according to the first-grade index score.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (10)
1. A user side comprehensive energy efficiency evaluation method based on a neural network is characterized by comprising the following steps: the method comprises the following steps:
acquiring energy efficiency index data of a user to be evaluated, wherein the energy efficiency index data are each secondary energy efficiency index data corresponding to each primary energy efficiency index in a preset index system;
inputting the secondary energy efficiency index data of the user to be evaluated into a pre-trained comprehensive energy efficiency evaluation model to obtain a primary energy efficiency index evaluation result of the user to be evaluated, which is output by the comprehensive energy efficiency evaluation model;
the pre-trained comprehensive energy efficiency evaluation model adopts a neural network, the neural network takes secondary energy efficiency index data as input, takes each primary energy efficiency index evaluation result corresponding to a secondary energy efficiency index as output, and training samples are known primary energy efficiency index evaluation results and corresponding secondary energy efficiency index data.
2. The user-side comprehensive energy efficiency evaluation method based on the neural network according to claim 1, characterized in that: the first-level energy efficiency index at least comprises one of economic benefit, electric energy quality, demand side management, production efficiency and environment index.
3. The method for evaluating the comprehensive energy efficiency of the user side based on the neural network as claimed in claim 2, wherein: the secondary energy efficiency index of the economic benefit index at least comprises one of investment cost, operation cost and operation and maintenance cost;
the secondary energy efficiency index of the power quality index at least comprises one of voltage deviation, power deviation, load rate, grid frequency deviation, three-phase unbalance rate and harmonic distortion rate;
the secondary energy efficiency index of the demand side management index at least comprises one of new energy equipment energy efficiency, conveying efficiency, lighting system energy efficiency, air conditioning system energy efficiency, power consumption peak-valley time period and energy consumption behavior analysis;
the secondary energy efficiency index of the production efficiency index at least comprises one of output value total, unit output value energy efficiency, production system energy efficiency and energy utilization equipment energy efficiency;
the secondary energy efficiency index of the environmental index at least comprises one of fuel consumption, pollutant emission and electromagnetic environmental pollution.
4. The method for evaluating the comprehensive energy efficiency of the user side based on the neural network as claimed in claim 2, wherein:
the first-level energy efficiency index evaluation result is a first-level energy efficiency index score, the first-level energy efficiency index score in the training sample is obtained through expert assignment scoring, and the scoring standard is as follows:
for the economic benefit index, scoring by taking whether the loss and the profit amount are as reference;
for the power quality index, judging the power quality as a reference score according to whether the detected power parameter curve is abnormally fluctuated, abnormal times and frequency;
scoring the demand side management indexes by taking whether the demand side management indexes participate in peak clipping and valley filling or not and whether the demand side management indexes participate in clean energy consumption actively or not as reference;
for the production efficiency index, the production value and energy consumption are taken as data basis and are used as reference scoring;
and as for the environmental index, scoring by taking the environmental index which is in accordance with the national regulation as a reference.
5. The user-side comprehensive energy efficiency evaluation method based on the neural network according to claim 1, characterized in that: and further comprising the step of carrying out data preprocessing on the secondary energy efficiency index data to be input into the comprehensive energy efficiency evaluation model, wherein the data preprocessing comprises deleting abnormal values and/or data normalization.
6. The user-side comprehensive energy efficiency evaluation method based on the neural network according to claim 1, characterized in that: the number of neurons in an input layer of the neural network is the number of secondary energy efficiency indexes, and the number of neurons in an output layer of the neural network is the number of primary energy efficiency indexes.
7. The user-side comprehensive energy efficiency evaluation method based on the neural network according to claim 1, characterized in that: the neural network training comprises initializing a network, inputting a training sample, setting network parameters, adjusting weight and threshold values, calculating errors, training until the error output by the network is reduced to the minimum error threshold value or the maximum iteration number is reached, otherwise, updating the weight values and continuing training.
8. The user-side comprehensive energy efficiency evaluation method based on the neural network according to claim 1, characterized in that: the first-level energy efficiency index evaluation result is a first-level energy efficiency index score; the method further comprises the following steps:
calculating the average value of the primary energy efficiency index scores of the users as the comprehensive energy efficiency score of the users;
determining a comprehensive energy efficiency grade of a user to be evaluated according to the comprehensive energy efficiency grade of the user and a preset energy efficiency grade determination rule;
the comprehensive energy efficiency grade comprises a plurality of grades corresponding to a plurality of comprehensive energy efficiency grading ranges; the preset energy efficiency grade determination rule is as follows: and determining a corresponding comprehensive energy efficiency grade according to the comprehensive energy efficiency grading range to which the user comprehensive energy efficiency grade belongs.
9. The user-side comprehensive energy efficiency evaluation method based on the neural network according to claim 8, characterized in that: the comprehensive energy efficiency grading range division step corresponding to each grade in the comprehensive energy efficiency grades comprises the following steps:
sorting the comprehensive energy efficiency scores corresponding to the plurality of users from large to small;
sequentially segmenting the sorted user comprehensive energy efficiency scoring sequence according to a proportional threshold, wherein each segment corresponds to one comprehensive energy efficiency grade, and the comprehensive energy efficiency grades corresponding to the segments sequentially represent that the user energy efficiency level is from high to low according to the sequence of the comprehensive energy efficiency scoring sequence from front to back;
and the numerical value between the minimum value and the maximum value of the user comprehensive energy efficiency score in each segment is the score range corresponding to the energy efficiency grade.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010798317.XA CN112016815A (en) | 2020-08-10 | 2020-08-10 | User side comprehensive energy efficiency evaluation method based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010798317.XA CN112016815A (en) | 2020-08-10 | 2020-08-10 | User side comprehensive energy efficiency evaluation method based on neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112016815A true CN112016815A (en) | 2020-12-01 |
Family
ID=73499487
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010798317.XA Pending CN112016815A (en) | 2020-08-10 | 2020-08-10 | User side comprehensive energy efficiency evaluation method based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112016815A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113361870A (en) * | 2021-05-20 | 2021-09-07 | 国网浙江省电力有限公司湖州供电公司 | Method for evaluating energy development level by using electric power data |
CN114760215A (en) * | 2022-03-11 | 2022-07-15 | 安徽师范大学 | Method and system for monitoring data transmission performance of computer network |
CN115393349A (en) * | 2022-10-26 | 2022-11-25 | 长春工程学院 | Method and system for evaluating quality of Changbai jade |
CN117011698A (en) * | 2023-06-25 | 2023-11-07 | 重庆市地理信息和遥感应用中心(重庆市测绘产品质量检验测试中心) | Multi-dimensional and multi-model earth surface full coverage interpretation sample set evaluation method |
CN117011698B (en) * | 2023-06-25 | 2024-05-03 | 重庆市地理信息和遥感应用中心(重庆市测绘产品质量检验测试中心) | Multi-dimensional and multi-model earth surface full coverage interpretation sample set evaluation method |
-
2020
- 2020-08-10 CN CN202010798317.XA patent/CN112016815A/en active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113361870A (en) * | 2021-05-20 | 2021-09-07 | 国网浙江省电力有限公司湖州供电公司 | Method for evaluating energy development level by using electric power data |
CN114760215A (en) * | 2022-03-11 | 2022-07-15 | 安徽师范大学 | Method and system for monitoring data transmission performance of computer network |
CN115393349A (en) * | 2022-10-26 | 2022-11-25 | 长春工程学院 | Method and system for evaluating quality of Changbai jade |
CN117011698A (en) * | 2023-06-25 | 2023-11-07 | 重庆市地理信息和遥感应用中心(重庆市测绘产品质量检验测试中心) | Multi-dimensional and multi-model earth surface full coverage interpretation sample set evaluation method |
CN117011698B (en) * | 2023-06-25 | 2024-05-03 | 重庆市地理信息和遥感应用中心(重庆市测绘产品质量检验测试中心) | Multi-dimensional and multi-model earth surface full coverage interpretation sample set evaluation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112016815A (en) | User side comprehensive energy efficiency evaluation method based on neural network | |
CN110991786B (en) | 10kV static load model parameter identification method based on similar daily load curve | |
CN109461025B (en) | Electric energy substitution potential customer prediction method based on machine learning | |
CN104809658B (en) | A kind of rapid analysis method of low-voltage distribution network taiwan area line loss | |
CN112990500B (en) | Transformer area line loss analysis method and system based on improved weighted gray correlation analysis | |
CN113205207A (en) | XGboost algorithm-based short-term power consumption load fluctuation prediction method and system | |
CN112819225A (en) | Carbon market price prediction method based on BP neural network and ARIMA model | |
CN111539657A (en) | Typical electricity consumption industry load characteristic classification and synthesis method combined with user daily electricity consumption curve | |
CN115860173A (en) | Construction and prediction method and medium of carbon emission prediction model based on Stacking algorithm | |
CN113706328A (en) | Intelligent manufacturing capability maturity evaluation method based on FASSA-BP algorithm | |
CN113962477A (en) | Industrial electric quantity association aggregation prediction method, device, equipment and storage medium | |
CN111160719A (en) | Two-network fused multi-index evaluation method | |
CN116108953A (en) | Rural power demand prediction based on DE-GWO-SVR | |
CN114004525A (en) | Electric energy substitution benefit evaluation method facing user side based on fuzzy comprehensive evaluation method | |
CN114638465A (en) | Acquisition terminal network signal quality evaluation method based on secondary scoring | |
CN114118551A (en) | Hydrogen energy industry chain structure optimization simulation method based on system dynamics | |
CN113327047A (en) | Power marketing service channel decision method and system based on fuzzy comprehensive model | |
CN113159535A (en) | Software service performance evaluation method based on entropy weight method | |
CN111353707A (en) | Scientific and technological input performance evaluation method based on data envelope analysis and BP neural network | |
CN112348066A (en) | Line uninterrupted power rating evaluation method based on gray clustering algorithm | |
CN117236532B (en) | Load data-based electricity consumption peak load prediction method and system | |
CN117592666B (en) | Multidimensional carbon emission data acquisition accounting system based on enterprise data | |
CN117540987A (en) | Industrial land planning method and device, electronic equipment and storage medium | |
CN116307781A (en) | Comprehensive energy efficiency diagnosis method based on AHP-entropy weight and unknown measure theory | |
CN114881705A (en) | New energy automobile sales prediction method based on least square support vector machine |
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: 20201201 |
|
RJ01 | Rejection of invention patent application after publication |