CN111275367B - Regional comprehensive energy system energy efficiency state evaluation method - Google Patents
Regional comprehensive energy system energy efficiency state evaluation method Download PDFInfo
- Publication number
- CN111275367B CN111275367B CN202010291349.0A CN202010291349A CN111275367B CN 111275367 B CN111275367 B CN 111275367B CN 202010291349 A CN202010291349 A CN 202010291349A CN 111275367 B CN111275367 B CN 111275367B
- Authority
- CN
- China
- Prior art keywords
- energy efficiency
- energy
- efficiency state
- index
- regional
- 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.)
- Active
Links
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a regional comprehensive energy system energy efficiency state evaluation method, which comprises the steps of carrying out multi-index synchronous clustering on historical operating data of a regional comprehensive energy system by adopting a Gaussian mixture model, and selecting a sample with the highest renewable energy permeability as a reference sample for energy efficiency state evaluation; constructing a regional comprehensive energy system energy efficiency state evaluation model by adopting a conditional variation self-encoder method; and calculating the energy efficiency state index of the regional comprehensive energy system and determining an energy efficiency state comment according to the energy efficiency state index. In the operation process of the regional comprehensive energy system, the overall energy efficiency state of the system can be evaluated, and the improvement of the renewable energy consumption proportion and the utilization efficiency of the system is further promoted while the safe and reliable operation of the system is ensured.
Description
Technical Field
The invention belongs to the technical field of energy efficiency state monitoring and evaluation of energy systems, and particularly relates to a regional comprehensive energy system energy efficiency state evaluation method.
Background
The comprehensive energy system aims at high-efficiency clean utilization of energy, takes large-scale renewable energy consumption as background, and realizes cascade utilization of different grades of energy through scientific coordination and scheduling of different energy supply links such as electricity, heat, gas and cold; by means of multi-energy complementation, the large-scale access and efficient utilization of renewable energy sources are promoted, and the flexibility, safety and economy of an energy supply system are improved. The comprehensive energy system is one of the important technological development directions in the energy industry in the 21 st century as the next generation of intelligent energy system.
The regional integrated energy system no longer emphasizes the dominant role of a single energy source, but focuses more on complementary interaction and synergy due to multi-energy coupling. Therefore, to ensure efficient operation of the system, the system problems such as effective access of renewable energy and minimum operation energy loss need to be considered cooperatively, and the equipment problems such as the use efficiency characteristic of the energy conversion unit and pollutant emission of the terminal equipment need to be considered.
The energy efficiency state evaluation problem of the regional comprehensive energy system is a multi-attribute decision problem, and the existing research mostly adopts a method of combining evaluation index selection and index weighting values to determine an evaluation scheme. The evaluation criterion is usually selected from a design value or a model calculation value. However, when the regional integrated energy system is actually operated, the regional integrated energy system is influenced by internal and external operation boundaries (environment, climate, working conditions, user demand diversity and the like), is a high-dimensional, time-varying and nonlinear system, and inevitably has a large deviation from an actual operation state by taking a design value or a model calculation value as an evaluation reference, so that the regional integrated energy system is limited in engineering application.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method for evaluating energy efficiency state of a regional integrated energy system, aiming at the above-mentioned defects of the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: the method for evaluating the energy efficiency state of the regional comprehensive energy system is constructed and comprises the following steps:
step 3, taking historical operation data in the reference sample as an energy efficiency state index, and constructing a regional comprehensive energy system energy efficiency state evaluation model by adopting a condition variational self-encoder method;
step 4, calculating an energy efficiency state index of the regional comprehensive energy system;
step 5, determining the comment grade, namely estimating the probability density distribution of the energy efficiency state index by adopting a Gaussian mixture model, and determining different comment grade thresholds of the energy efficiency state by setting different confidence coefficients;
and 6, evaluating the energy efficiency state in real time, calculating the average value of the energy efficiency state index in the window after the highest value and the lowest value are removed by adopting a sliding window detection technology, and determining the energy efficiency state comment of the system.
Wherein, step 2 includes:
step 201, dividing the historical operation data into working conditions according to the environmental temperature, the environmental wind speed, the solar radiation intensity and the load requirement;
step 202, calculating the permeability of renewable energy of the regional integrated energy system, wherein the permeability of renewable energy is the ratio of the generated energy of the renewable energy to the total generated energy of the system;
step 203, performing multi-index synchronous clustering on the historical data of the energy state indexes based on a Gaussian mixture model;
and 204, selecting energy efficiency reference state samples under various working conditions as reference samples for evaluating the energy efficiency state of the system by taking the maximum permeability of the renewable energy source of the system as a target.
Wherein, step 3 includes:
step 301, constructing an energy efficiency state observation vector X (i) ═ X under an optional operation condition c1(i)X2(i)...Xn(i)]TWherein X (i) represents an energy efficiency index observation vector of the system at the ith time, Xk(i) (k is 1,2, …, n) represents the k-th energy efficiency state index value at the i-th time, and n represents the number of energy efficiency state indexes;
and step 302, taking the energy efficiency state observation vector X (i) and the operation working condition c as input, and constructing an energy efficiency state evaluation model based on a condition variational self-encoder algorithm.
Wherein, based on the conditional variation autoencoder model meterCalculating the posterior probability and prior probability distribution, and calculating KL dispersity DKLAnd the probability of reconstruction RL is determined,l is the number of samples, and log (p (x | z)) is the log likelihood of the input samples under the condition of an implicit variable z obtained by posterior distribution sampling of a variational self-encoder, so that the energy efficiency state index of the regional integrated energy system is SI (equal to RL-D)KL。
Wherein, step 5 includes:
step 501, estimating probability density distribution of an energy efficiency state index by adopting a Gaussian mixture model;
step 502, defining a comment set of energy efficiency states of the regional integrated energy system: a ═ A1,A2,A3{ excellent, good, poor };
step 503, setting a corresponding energy efficiency state index as an evaluation threshold when the confidence coefficient α is 70%; when the confidence α is 95%, the corresponding energy efficiency state index serves as a threshold for evaluating a good state.
Wherein, step 6 includes:
step 601, selecting an energy efficiency state index time sequence with the length of n from the starting time i to the front: SI (Standard interface)i←i-n+1=[SIi-n+1,…,SIi-1,SIi],n≥0;
Step 602, counting and removing the maximum and minimum values in the window data, according to the formulaCalculating the average value of the energy efficiency state indexes in the window;
step 603, when the incremental step is k, obtaining a new time sequence: SI (Standard interface)i+k←i+k-n+1=[SIi+k-n+1,…SIi+k-1,SIi+k]N is more than or equal to 0, k is more than or equal to 0, and the operation of the step 602 is repeated to obtainSo that the process is recurred.
And (2) acquiring and storing values of signals such as steam temperature, pressure, flow, pollutant discharge amount, load, environment temperature, environment wind speed, solar radiation intensity, fan output, solar power generation amount and the like of each main device in the step 1 every minute.
The building of the energy efficiency state evaluation model in step 302 includes:
step A, inputting an energy efficiency state observation vector X (i) and an operation working condition c, and calculating by using an encoder to obtain a mean value in variation posterior distributionSum variance
Step B, according to the heavy parameter transformation, the formulaCalculating a hidden variable z;
step C, calculating the hidden variable z through a decoder to obtain a reconstructed variableMean value of distribution muθ(z, c) and variance σθ(z,c);
And D, calculating the log-likelihood of the input energy efficiency state observation vector.
Wherein, the step 203 of performing multi-index synchronous clustering on the historical data of the energy status indexes based on the gaussian mixture model comprises:
a1, selecting the number K of sub models of the Gaussian mixture model, wherein K is the clustering number; the probability distribution form of the multivariate Gaussian mixture model is set as follows:wherein X is a historical operating data vector of the n-dimensional energy efficiency state index, and X is [ X ]1,x2,…,xn]T;ωkIs the weight of the submodel, and ωk≥0,φ(X|θk) Is a multi-dimensional single gaussian probability density function of the kth sub-model,wherein, mukSum ΣkRespectively representing the mean and covariance matrix of the kth sub-model;
step B1, solving formula based on maximum likelihood estimation algorithmEstimate mu of the Gaussian mixture modelk、∑kAnd ωk;
Step C1, respectively bringing historical operating data X (i) at different moments into K Gaussian distribution functions, calculating the probability of each category, and selecting the category with the highest probability value as the final category of the group of operating data; wherein x (i) represents operation data corresponding to the energy efficiency state index at the ith time.
Different from the prior art, the energy efficiency state evaluation method of the regional integrated energy system carries out multi-index synchronous clustering on historical operating data of the regional integrated energy system by adopting a Gaussian mixture model, selects a sample with the highest renewable energy permeability as a reference sample, takes the reference sample as an energy efficiency state index, and constructs an energy efficiency state evaluation model of the regional integrated energy system by adopting a condition variational self-encoder method; and calculating the energy efficiency state index of the regional comprehensive energy system and determining an energy efficiency state comment according to the energy efficiency state index. In the operation process of the regional comprehensive energy system, the overall energy efficiency state of the system can be evaluated, and the improvement of the renewable energy consumption proportion and the utilization efficiency of the system is further promoted while the safe and reliable operation of the system is ensured.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
fig. 1 is a schematic flow chart of a method for evaluating energy efficiency states of a regional integrated energy system according to the present invention.
Fig. 2 is a flowchart of a reference state determination method of the energy efficiency state evaluation method of the regional integrated energy system provided by the invention.
Fig. 3 is a flow chart of state evaluation model construction of the method for evaluating the energy efficiency state of the regional integrated energy system provided by the invention.
Fig. 4 is a flow chart of determining a status comment level of the energy efficiency status evaluation method of the regional integrated energy system according to the present invention.
Fig. 5 is a statistical schematic diagram of an average energy efficiency state index of the energy efficiency state evaluation method of the regional integrated energy system provided by the invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
Fig. 1 is a general flowchart of a method for evaluating the energy efficiency state of a regional integrated energy system. The method for evaluating the energy efficiency state of the regional comprehensive energy system comprises the following steps:
the invention relates to an energy conversion device, comprising: the system comprises a gas turbine, a waste heat boiler, a wind driven generator and a solar photovoltaic power generation device. The method is characterized in that signals of steam temperature, pressure, flow, pollutant discharge amount, load, environment temperature, environment wind speed, solar radiation intensity, fan output, solar generated energy and the like of main energy conversion equipment are collected and are introduced into a data collection and analysis system from a Distributed Control System (DCS) and an Energy Management System (EMS) through an OPC communication mode. Under the principle that the analysis requirement can be met and the storage space can be saved as far as possible, the numerical values of signals such as steam temperature, pressure, flow, load, ambient temperature, ambient wind speed, solar radiation intensity, fan output, solar power generation and the like are collected every minute and stored.
in the invention, a Gaussian mixture model is adopted to determine the system operation reference state, the similarity of historical data is utilized to position the system energy efficiency state information under the historical comparable working condition, and the rule of the diversity and the repeatability of the system energy efficiency state under multiple boundaries is disclosed.
Fig. 2 is a flowchart of a method for determining an energy efficiency reference state of a regional integrated energy system, where step 2 includes:
step 201, dividing the historical operation data into working conditions according to the environmental temperature, the environmental wind speed, the solar radiation intensity and the load requirement;
step 202, calculating the permeability of renewable energy of the regional integrated energy system, wherein the permeability of renewable energy is the ratio of the generated energy of the renewable energy to the total generated energy of the system;
step 203, performing multi-index synchronous clustering on the historical data of the energy state indexes based on a Gaussian mixture model;
based on a Gaussian mixture model, the step of carrying out multi-index synchronous clustering on the historical data of the energy status indexes comprises the following steps:
a1, selecting the number K of sub models of the Gaussian mixture model, wherein K is the clustering number; the probability distribution form of the multivariate Gaussian mixture model is set as follows:wherein X is a historical operating data vector of the n-dimensional energy efficiency state index, and X is [ X ]1,x2,…,xn]T;ωkIs the weight of the submodel, and ωk≥0,φ(X|θk) Is a multi-dimensional single gaussian probability density function of the kth sub-model,wherein, mukSum ΣkRespectively representing the mean and covariance matrix of the kth sub-model;
step B1, solving formula based on maximum likelihood estimation algorithmEstimate mu of the Gaussian mixture modelk、∑kAnd ωk;
Step C1, respectively bringing historical operating data X (i) at different moments into K Gaussian distribution functions, calculating the probability of each category, and selecting the category with the highest probability value as the final category of the group of operating data; wherein x (i) represents operation data corresponding to the energy efficiency state index at the ith time.
And 204, selecting energy efficiency reference state samples under various working conditions as reference samples for evaluating the energy efficiency state of the system by taking the maximum permeability of the renewable energy source of the system as a target.
And selecting the data obtained by clustering in the step 203 in the mode of the step 204, and finally determining a reference sample.
And 3, taking historical operation data in the reference sample as an energy efficiency state index, and constructing a regional comprehensive energy system energy efficiency state evaluation model by adopting a condition variational self-encoder method.
In the invention, the real state of the system is estimated by adopting the reference state model obtained by historical data learning, and the variability of the system operation boundary and the dynamic complexity of the energy efficiency state information are considered.
Fig. 3 is a flow chart of a regional integrated energy system energy efficiency state evaluation model construction, where step 3 includes:
step 301, and constructing energy efficiency state under optional operation working condition cObservation vector X (i) ═ X1(i)X2(i)...Xn(i)]TWherein X (i) represents an energy efficiency index observation vector of the system at the ith time, Xk(i) (k is 1,2, …, n) represents the k-th energy efficiency state index value at the i-th time, and n represents the number of energy efficiency state indexes;
and step 302, taking the energy efficiency state observation vector X (i) and the operation working condition c as input, and constructing an energy efficiency state evaluation model based on a condition variational self-encoder algorithm.
In the present invention, the constructing of the energy efficiency state evaluation model in step 302 includes:
step A, inputting an energy efficiency state observation vector X (i) and an operation working condition c, and calculating by using an encoder to obtain a mean value in variation posterior distributionSum variance
Step B, according to the heavy parameter transformation, the formulaCalculating a hidden variable z;
step C, calculating the hidden variable z through a decoder to obtain a reconstructed variableMean value of distribution muθ(z, c) and variance σθ(z,c);
And D, calculating the log-likelihood of the input energy efficiency state observation vector.
Step 4, the formula SI is equal to RL-DKLAnd calculating the energy efficiency state index SI of the regional comprehensive energy system.
Calculating KL dispersity D based on posterior probability and prior probability distribution obtained by calculation of conditional variational self-encoder modelKLAnd the probability of reconstruction RL is determined,l is the number of samples, and log (p (x | z)) is the log-likelihood of the input sample under the condition of an implicit variable z obtained by the posterior distribution sampling of the variational self-encoder.
And 5, determining the comment grade, estimating the probability density distribution of the energy efficiency state index by adopting a Gaussian mixture model, and determining different energy efficiency state comment grade thresholds by setting different confidence coefficients.
Fig. 4 is a flow chart of the regional integrated energy system energy efficiency status comment level determination, wherein the step 5 comprises:
step 501, estimating probability density distribution of an energy efficiency state index by adopting a Gaussian mixture model;
step 502, defining a comment set of energy efficiency states of the regional integrated energy system: a ═ A1,A2,A3{ excellent, good, poor };
step 503, setting a corresponding energy efficiency state index as an evaluation threshold when the confidence coefficient α is 70%; when the confidence α is 95%, the corresponding energy efficiency state index serves as a threshold for evaluating a good state.
And 6, evaluating the energy efficiency state in real time, calculating the average value of the energy efficiency state index in the window after the highest value and the lowest value are removed by adopting a sliding window detection technology, and determining the energy efficiency state comment of the system.
In the invention, a sliding window detection technology is adopted, and the evaluation result of the energy efficiency state is determined by counting the average value of the energy efficiency state indexes after the maximum value and the minimum value are removed in window time, so that the influence of uncertain factors and random interference (such as measurement errors of a sensor) on the energy efficiency state indexes is eliminated, and the accuracy and the reliability of the energy efficiency state evaluation are improved.
Fig. 5 is a statistical schematic diagram of the average energy efficiency state index of the regional integrated energy system, where step 6 includes:
step 601, selecting an energy efficiency state index time sequence with the length of n from the starting time i to the front: SI (Standard interface)i←i-n+1=[SIi-n+1,…,SIi-1,SIi],n≥0;
Step 602, counting and removing the most of the window dataLarge and minimum values, from the formulaCalculating the average value of the energy efficiency state indexes in the window;
step 603, when the incremental step is k, obtaining a new time sequence: SI (Standard interface)i+k←i+k-n+1=[SIi+k-n+1,…SIi+k-1,SIi+k]N is more than or equal to 0, k is more than or equal to 0, and the operation of the step 602 is repeated to obtainSo that the process is recurred.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (6)
1. A method for evaluating the energy efficiency state of a regional integrated energy system is characterized by comprising the following steps:
step 1, collecting, analyzing and storing energy efficiency state indexes: synchronously acquiring historical operating data of each energy conversion device of the regional comprehensive energy system, wherein the historical operating data comprises steam temperature, pressure, flow, pollutant discharge amount, load, environment temperature, environment wind speed, solar radiation intensity, fan output and solar energy generating capacity signals, calculating the energy consumption rate of corresponding devices, and establishing a historical database;
step 2, determining the energy efficiency reference state of the regional comprehensive energy system: performing multi-index synchronous clustering on the collected historical operating data by adopting a Gaussian mixture model, and selecting a sample with the highest renewable energy permeability as a reference sample for evaluating the energy efficiency state of the regional comprehensive energy system;
wherein the step 2 comprises:
step 201, dividing the historical operation data into working conditions according to the environmental temperature, the environmental wind speed, the solar radiation intensity and the load requirement;
step 202, calculating the permeability of renewable energy of the regional integrated energy system, wherein the permeability of renewable energy is the ratio of the generated energy of the renewable energy to the total generated energy of the system;
step 203, performing multi-index synchronous clustering on the historical data of the energy state indexes based on a Gaussian mixture model;
204, selecting energy efficiency reference state samples under various working conditions as reference samples for evaluating the energy efficiency state of the system by taking the maximum permeability of the renewable energy source of the system as a target;
step 3, taking historical operation data in the reference sample as an energy efficiency state index, and constructing a regional comprehensive energy system energy efficiency state evaluation model by adopting a conditional variation self-encoder algorithm;
wherein the step 3 comprises:
step 301, constructing an energy efficiency state observation vector X (i) ═ X under an optional operation condition c1(i) X2(i)...Xn(i)]TWherein X (i) represents an observation vector of an energy efficiency state index of the system at the i-th time, Xk(i) Representing the kth energy efficiency state index value at the ith time, wherein k is 1,2, …, n and n represents the number of energy efficiency state indexes;
step 302, taking an energy efficiency state observation vector X (i) and an operation condition c as input, and constructing an energy efficiency state evaluation model based on a condition variational self-encoder algorithm;
the constructing of the energy efficiency state evaluation model in step 302 includes:
step A, inputting an energy efficiency state observation vector X (i) and an operation working condition c, and calculating by using an encoder to obtain a mean value in variation posterior distributionSum variance
step C, calculating the hidden variable z through a decoder to obtain a reconstructed variableMean value of distribution muθ(z, c) and variance σθ(z,c);
D, calculating the log-likelihood of the input energy efficiency state observation vector;
step 4, calculating an energy efficiency state index of the regional comprehensive energy system;
step 5, determining the comment grade, namely estimating the probability density distribution of the energy efficiency state index by adopting a Gaussian mixture model, and determining different comment grade thresholds of the energy efficiency state by setting different confidence coefficients;
and 6, evaluating the energy efficiency state in real time, calculating the average value of the energy efficiency state index in the window after the highest value and the lowest value are removed by adopting a sliding window detection technology, and determining the energy efficiency state comment of the system.
2. The method for evaluating the energy efficiency state of the regional integrated energy system according to claim 1, wherein the KL dispersion degree D is calculated based on the posterior probability and the prior probability distribution calculated by the conditional variational self-encoder algorithmKLAnd the probability of reconstruction RL is determined,l is the number of samples, and log (p (x | z)) is the log likelihood of the input samples under the condition of an implicit variable z obtained by posterior distribution sampling of a variational self-encoder, so that the energy efficiency state index of the regional integrated energy system is SI (equal to RL-D)KL。
3. The method for evaluating the energy efficiency status of the regional integrated energy system according to claim 1, wherein the step 5 comprises:
step 501, estimating probability density distribution of an energy efficiency state index by adopting a Gaussian mixture model;
step 502, defining a comment set of energy efficiency states of the regional integrated energy system: a ═ A1,A2,A3{ excellent, good, poor };
step 503, setting a corresponding energy efficiency state index as an evaluation threshold when the confidence coefficient α is 70%; when the confidence α is 95%, the corresponding energy efficiency state index serves as a threshold for evaluating a good state.
4. The method for evaluating the energy efficiency status of the regional integrated energy system according to claim 1, wherein the step 6 comprises:
step 601, selecting an energy efficiency state index time sequence with the length of n from the starting time i to the front: SI (Standard interface)i←i-n+1=[SIi-n+1,…,SIi-1,SIi],n≥0;
Step 602, counting and removing the maximum and minimum values in the window data, according to the formulaCalculating the average value of the energy efficiency state indexes in the window;
5. The method for evaluating the energy efficiency state of the regional energy integration system according to claim 1, wherein the values of the steam temperature, the pressure, the flow rate, the pollutant discharge amount, the load, the ambient temperature, the ambient wind speed, the solar radiation intensity, the fan output and the solar power generation amount signal of each energy conversion device in the step 1 are collected and stored once per minute.
6. The method for evaluating the energy efficiency state of the regional integrated energy system according to claim 1, wherein the step 203 of performing multi-index synchronous clustering on the historical data of the energy efficiency state indexes based on a gaussian mixture model comprises:
a1, selecting the number K of sub models of the Gaussian mixture model, wherein K is the clustering number; the probability distribution form of the multivariate Gaussian mixture model is set as follows:wherein X is a historical operating data vector of the n-dimensional energy efficiency state index, and X is [ X ]1,x2,…,xn]T;ωkIs the weight of the submodel, and ωk≥0,φ(X|θk) Is a multi-dimensional single gaussian probability density function of the kth sub-model,wherein, mukSum ΣkRespectively representing the mean and covariance matrix of the kth sub-model;
step B1, solving formula based on maximum likelihood estimation algorithmEstimate mu of the Gaussian mixture modelk、∑kAnd ωk;
Step C1, respectively bringing historical operating data X (i) at different moments into K Gaussian distribution functions, calculating the probability of each category, and selecting the category with the highest probability value as the final category of the group of operating data; wherein x (i) represents operation data corresponding to the energy efficiency state index at the ith time.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2019104177728 | 2019-05-20 | ||
CN201910417772.8A CN110210730A (en) | 2019-05-20 | 2019-05-20 | A kind of regional complex energy resource system energy efficiency state evaluation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111275367A CN111275367A (en) | 2020-06-12 |
CN111275367B true CN111275367B (en) | 2021-01-01 |
Family
ID=67787793
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910417772.8A Pending CN110210730A (en) | 2019-05-20 | 2019-05-20 | A kind of regional complex energy resource system energy efficiency state evaluation method |
CN202010291349.0A Active CN111275367B (en) | 2019-05-20 | 2020-04-14 | Regional comprehensive energy system energy efficiency state evaluation method |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910417772.8A Pending CN110210730A (en) | 2019-05-20 | 2019-05-20 | A kind of regional complex energy resource system energy efficiency state evaluation method |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN110210730A (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110825583B (en) * | 2019-10-29 | 2023-07-28 | 湘潭大学 | Energy efficiency qualitative assessment technology for multi-index fusion of cloud data center |
CN112414694B (en) * | 2020-06-12 | 2021-08-27 | 北京航空航天大学 | Equipment multistage abnormal state identification method and device based on multivariate state estimation technology |
CN111898903A (en) * | 2020-07-28 | 2020-11-06 | 北京科技大学 | Method and system for evaluating uniformity and comprehensive quality of steel product |
CN112085400A (en) * | 2020-09-15 | 2020-12-15 | 天元大数据信用管理有限公司 | Comprehensive and efficient credit rating index empowerment method |
CN112149353B (en) * | 2020-09-24 | 2024-03-22 | 南京大学 | Method for identifying DNAPL pollutant distribution in underground aquifer based on convolutional neural network |
CN112329868B (en) * | 2020-11-10 | 2023-08-01 | 西安电子科技大学 | CLARA clustering-based manufacturing and processing equipment group energy efficiency state evaluation method |
CN112836920A (en) * | 2020-12-01 | 2021-05-25 | 北方联合电力有限责任公司乌拉特发电厂 | Coal electric unit energy efficiency state evaluation method and device and coal electric unit system |
CN112865083B (en) * | 2021-01-21 | 2022-07-05 | 浙江大学 | Real-time running state evaluation method for power system containing renewable energy sources |
CN113421169B (en) * | 2021-05-08 | 2022-08-30 | 浙江大学 | Method and system for analyzing reliability-efficiency diffusion structure of integrated energy system |
CN117494032B (en) * | 2024-01-03 | 2024-04-02 | 长春市鸣玺科技有限公司 | Building energy consumption real-time monitoring control system and method |
CN117575373B (en) * | 2024-01-17 | 2024-04-26 | 北京恒信启华信息技术股份有限公司 | Equipment energy consumption monitoring and analyzing method and system based on big data |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130218408A1 (en) * | 2012-02-17 | 2013-08-22 | Chrysler Group Llc | Method and apparatus for improving vehicle fuel economy with energy storage efficiency model |
CN106127388A (en) * | 2016-06-24 | 2016-11-16 | 南瑞(武汉)电气设备与工程能效测评中心 | The energy efficiency evaluating method of high energy-consuming enterprises |
CN106600104A (en) * | 2016-11-07 | 2017-04-26 | 国网江苏省电力公司 | Evaluation method for evaluating energy efficiency of integrated energy system |
CN107067108A (en) * | 2017-04-14 | 2017-08-18 | 清华大学 | Meter and the garden integrated energy system energy efficiency evaluating method of regenerative resource access |
CN108460525A (en) * | 2018-02-24 | 2018-08-28 | 南方电网科学研究院有限责任公司 | A kind of comprehensive energy utilization ratio appraisal procedure for distribution system of providing multiple forms of energy to complement each other |
-
2019
- 2019-05-20 CN CN201910417772.8A patent/CN110210730A/en active Pending
-
2020
- 2020-04-14 CN CN202010291349.0A patent/CN111275367B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN110210730A (en) | 2019-09-06 |
CN111275367A (en) | 2020-06-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111275367B (en) | Regional comprehensive energy system energy efficiency state evaluation method | |
CN108376262B (en) | Analytical model construction method for typical characteristics of wind power output | |
CN111275288B (en) | XGBoost-based multidimensional data anomaly detection method and device | |
CN111612651B (en) | Abnormal electric quantity data detection method based on long-term and short-term memory network | |
CN109598451B (en) | Non-invasive load identification method based on PCA (principal component analysis) and LSTM (least Square TM) neural network | |
CN109902340B (en) | Multi-source-load combined scene generation method considering complex meteorological coupling characteristics | |
CN111414717A (en) | XGboost-L ightGBM-based unit power prediction method | |
CN110362045B (en) | Marine doubly-fed wind turbine generator fault discrimination method considering marine meteorological factors | |
CN111027775A (en) | Step hydropower station generating capacity prediction method based on long-term and short-term memory network | |
CN110503153B (en) | Photovoltaic system fault diagnosis method based on differential evolution algorithm and support vector machine | |
CN113837464A (en) | Load prediction method of cogeneration boiler based on CNN-LSTM-Attention | |
CN109272258B (en) | Regional wind and solar power generation resource evaluation method based on K-means clustering | |
CN111242353A (en) | Wind power combined prediction modeling and prediction method | |
CN112418495A (en) | Building energy consumption prediction method based on longicorn stigma optimization algorithm and neural network | |
CN114119273A (en) | Park comprehensive energy system non-invasive load decomposition method and system | |
CN116796403A (en) | Building energy saving method based on comprehensive energy consumption prediction of commercial building | |
CN115409369A (en) | Comprehensive energy system reliability evaluation method based on mechanism and data hybrid driving | |
CN114595762A (en) | Photovoltaic power station abnormal data sequence extraction method | |
CN114298136A (en) | Wind speed prediction method based on local mean decomposition and deep learning neural network | |
CN111275238B (en) | Large-scale power station photovoltaic output sequence generation method based on hourly clear sky index | |
CN112132344A (en) | Short-term wind power prediction method based on similar day and FRS-SVM | |
CN112836876A (en) | Power distribution network line load prediction method based on deep learning | |
CN113095534A (en) | Wind power prediction method combining ARIMA and improved Elman neural network | |
CN116050592A (en) | Multi-dimensional photovoltaic power prediction method and system | |
CN110796292A (en) | Photovoltaic power short-term prediction method considering haze influence |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |