CN109214721A - A kind of long-term cool and thermal power load classification method in multi-energy system - Google Patents
A kind of long-term cool and thermal power load classification method in multi-energy system Download PDFInfo
- Publication number
- CN109214721A CN109214721A CN201811319743.XA CN201811319743A CN109214721A CN 109214721 A CN109214721 A CN 109214721A CN 201811319743 A CN201811319743 A CN 201811319743A CN 109214721 A CN109214721 A CN 109214721A
- Authority
- CN
- China
- Prior art keywords
- step3
- thermal power
- cool
- power load
- entropy
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000007774 longterm Effects 0.000 title claims abstract description 24
- 239000000284 extract Substances 0.000 claims abstract description 8
- 238000012706 support-vector machine Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of cool and thermal power load classification methods long-term in multi-energy system, and this method comprises the following steps: 1), acquiring long-term cool and thermal power load signal in multi-energy system；2), the cool and thermal power load signal of step 1) is pre-processed；3) Sample Entropy analysis, is carried out to by the pretreated cool and thermal power load signal of step 2), extracts validity feature entropy；4) the validity feature entropy that, step 3) is extracted classifies to cool and thermal power load signal using support vector machines learner；5), the load signal of the cool and thermal power load signal classification results of step 4) and step 1) is compared, determines recognition result.The present invention can accurately classify to cold and hot electric load long-term in multi-energy system.
Description
Technical field
The present invention relates to multiple-energy-source integrated system fields, more specifically to long-term cold and hot in a kind of multi-energy system
Electric load classification method.
Background technique
With internet, Internet of Things, cloud computing, the fast development of big data technology, global intelligent level is increasingly increased,
With the proposition of wisdom earth concept, the intelligent industries such as smart city, intelligence community, intelligent building, smart grid are global each
State rises successively, develops.Huge change also occurs for energy field, and China will strive building between the following twenty or thirty year "
Demand is rationalized, exploitation greenization, supply diversification, allotment is intelligent, utilize it is efficient " new energy system.It is renewable
The energy that the energy is led transition situation is good, world community all in the utilization for increasing renewable energy, the whole world 62% in 2016
Newly-increased electric power comes from renewable energy, and net newly-increased electric power of the U.S. in 2017 from renewable energy is more than 94%, energy topology
The increasingly complexity of structure more shows the irreplaceability of energy internet.The control management of new energy, traffic control exist
Indispensable status is occupied in energy intelligentized platform, the core of dynamically optimized scheduling is then load Predicting Technique, intelligence tune
Degree etc., intelligent scheduling platform is constituted by software and hardware combining, further realize for this energy internet real-time monitoring and
The whole network is controllable.
Energy system planning belongs to long-term optimization, solves the problems, such as the development of energy facilities on a larger time scale, invests to build.
The prediction technique of cold heat, electric load on long-term scale is the basis of energy system planning in the multipotency source supply system of region,
First it is necessary to cool and thermal power load classification long-term in carrying out, there has been no about cool and thermal power long-term in multi-energy system in the prior art
The report of load classification method.
Summary of the invention
The technical problem to be solved by the present invention is to propose long-term cool and thermal power load classification side in a kind of multi-energy system
Method.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of long-term cool and thermal power load classification method in multi-energy system is designed, this method comprises the following steps:
Step1 acquires long-term cold and hot electric load in multi-energy system.
Step2 pre-processes the cool and thermal power load signal of step Step1.
Step3 carries out Sample Entropy analysis to by the pretreated cool and thermal power load signal of step Step2, extracts effective
Characteristic Entropy.
Step4, the validity feature entropy that step Step3 is extracted, using support vector machines learner to cold and hot electric load
Signal is classified.
Step5 carries out the load signal of the cool and thermal power load signal classification results of step Step4 and step Step1 pair
Than determining recognition result.
In the above scheme, the step Step3 specifically includes the following steps:
Step3-1 decomposes cool and thermal power load signal.
Step3-2, calculated load sample of signal entropy.
Step3-3 analyzes signal frequency domain details.
Step3-4 extracts Characteristic Entropy.
In the above scheme, the Sample Entropy in the Step3-2 step by step calculates step are as follows:
Step3-2-1 carries out coarse calculating to load signal；
Step3-2-2, changes obtained time series according to scale τ, and length N=L/ τ forms one group of m in order
N dimensional vector n: from Yτ(1) Y is arrivedτ(N-m+1)；
Step3-2-3 defines Yτ(i) and YτThe distance between (j) for both difference maximum one in corresponding element, i.e.,
,
And calculate the corresponding d [Y of each i valueτ(i)-Yτ(j)]；
Step3-2-4, given threshold value r count d [Y for each 1≤i≤N-m+1τ(i)-Yτ(j)] it is less than the number of r
Mesh and this number and the ratio apart from total N-m, are denoted as
Step3-2-5 averages to all the points, is denoted as Cτ,m(r), i.e.,
Step3-2-6 increases dimension to m+1, repeats step Step3-2-2 to Step3-2-5, obtain Cτ,m+1(r)；
Step3-2-7 calculates Sample Entropy:
In the above scheme, the extraction Characteristic Entropy in the Step3-4 step by step is the following steps are included: define three kinds of loads
Entropy growth rate before being mutated on scale is entropy gaining rate, is fitted to obtain slope using least square method, joint has physics
The Sample Entropy mean value composition characteristic amount (r of meaning1,r2)。
In the above scheme, support vector machines learner classifies to cool and thermal power load signal in the step Step4
Algorithm use Radial basis kernel function, classifier use one-to-one algorithm, specifically includes the following steps:
Step4-1, to given sample set (xi,yi), i=1,2 ... n, xi∈Rd, y ∈ { -1,1 } is category label, is passed through
Nonlinear transformationRd→Rn, input vector is mapped to n-dimensional space；
Step4-2 establishes hyperplane in higher dimensional space:
ω φ (X)+b=0 (2)
Wherein: weight
Step4-3, Optimal Separating Hyperplane optimization, i.e., in yi(ωφ(xi)+b) under >=1 constraint condition, classify plane Φ (ω)
=| | ω | |2/ 2 obtain minimum value；
Step4-4 introduces Lagrange multiplier ai>=0, it is converted into Novel Algorithm:
It obtains optimal
Step4-5, optimal classification function are as follows:
Introduce kernel function K, K (Xi,Xj)=φ (Xi)·φ(Xj), then
Compared with prior art, the invention has the following advantages:
The present invention can accurately classify to cold and hot electric load long-term in multi-energy system.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.
The present invention provides a kind of long-term cool and thermal power load classification method in multi-energy system, and this method comprises the following steps:
Step1 acquires long-term cold and hot electric load in multi-energy system.
Step2 pre-processes the cool and thermal power load signal of step Step1.
Step3 carries out Sample Entropy analysis to by the pretreated cool and thermal power load signal of step Step2, extracts effective
Characteristic Entropy.Step Step3 specifically includes the following steps:
Step3-1 decomposes cool and thermal power load signal.
Step3-2, calculated load sample of signal entropy.This step by step in Sample Entropy calculate step are as follows:
Step3-2-1 carries out coarse calculating to load signal；
Step3-2-2, changes obtained time series according to scale τ, and length N=L/ τ forms one group of m in order
N dimensional vector n: from Yτ(1) Y is arrivedτ(N-m+1)；
Step3-2-3 defines Yτ(i) and YτThe distance between (j) for both difference maximum one in corresponding element, i.e.,
,
And calculate the corresponding d [Y of each i valueτ(i)-Yτ(j)]；
Step3-2-4, given threshold value r count d [Y for each 1≤i≤N-m+1τ(i)-Yτ(j)] it is less than the number of r
Mesh and this number and the ratio apart from total N-m, are denoted as
Step3-2-5 averages to all the points, is denoted as Cτ,m(r), i.e.,
Step3-2-6 increases dimension to m+1, repeats step Step3-2-2 to Step3-2-5, obtain Cτ,m+1(r)；
Step3-2-7 calculates Sample Entropy:
Step3-3 analyzes signal frequency domain details.
Step3-4 extracts Characteristic Entropy.This step by step in extraction Characteristic Entropy the following steps are included: to define three kinds of loads prominent
Entropy growth rate before becoming on scale is fitted to obtain slope using least square method, joint has physics meaning into entropy gaining rate
The Sample Entropy mean value composition characteristic amount (r of justice1,r2)。
Step4, the validity feature entropy that step Step3 is extracted, using support vector machines learner to cold and hot electric load
Signal is classified.Support vector machines learner uses diameter to the algorithm that cool and thermal power load signal is classified in step Step4
To base kernel function, classifier uses one-to-one algorithm, specifically includes the following steps:
Step4-1, to given sample set (xi,yi), i=1,2 ... n, xi∈Rd, y ∈ { -1,1 } is category label, is passed through
Nonlinear transformationRd→Rn, input vector is mapped to n-dimensional space；
Step4-2 establishes hyperplane in higher dimensional space:
ω φ (X)+b=0 (2)
Wherein: weight
Step4-3, Optimal Separating Hyperplane optimization, i.e., in yi(ωφ(xi)+b) under >=1 constraint condition, classify plane Φ (ω)
=| | ω | |2/ 2 obtain minimum value；
Step4-4 introduces Lagrange multiplier ai>=0, it is converted into Novel Algorithm:
It obtains optimal
Step4-5, optimal classification function are as follows:
In order to avoid higher dimensional space complex calculation, kernel function K, K (X are introducedi,Xj)=φ (Xi)·φ(Xj), then
Step5 carries out the load signal of the cool and thermal power load signal classification results of step Step4 and step Step1 pair
Than determining recognition result.
By taking some region multipotency source supply system as an example, according to above method step, its medium-term and long-term cool and thermal power load is acquired
Data, referring to table 1, initial data length N=8760, scale τ=1~20, m=2, r=0.1SD, SD are original time series
Standard deviation, electric load region area takes 1000m2, the sample data being calculated is as shown in table 2 below:
In table 1 for a long time by when electric load data
The sample data and recognition result and the actual conditions table of comparisons being calculated in 2 the present embodiment of table
As shown in Table 2, using the cool and thermal power load signal classification results of the invention obtained and the complete phase of actual load classification
Together, illustrate that the present invention can accurately classify to cold and hot electric load long-term in multi-energy system.
It is above-mentioned that the embodiment of the present invention is described, but the invention is not limited to above-mentioned specific embodiment parties
Formula, the above mentioned embodiment is only schematical, rather than restrictive, and those skilled in the art are in this hair
Under bright enlightenment, without breaking away from the scope protected by the purposes and claims of the present invention, many forms can be also made, this
It is belonged within protection of the invention a bit.
Claims (5)
1. a kind of long-term cool and thermal power load classification method in multi-energy system, which is characterized in that this method comprises the following steps:
Step1 acquires long-term cold and hot electric load in multi-energy system；
Step2 pre-processes the cool and thermal power load signal of step Step1；
Step3 carries out Sample Entropy analysis to by the pretreated cool and thermal power load signal of step Step2, extracts validity feature
Entropy；
Step4, the validity feature entropy that step Step3 is extracted, using support vector machines learner to cool and thermal power load signal
Classify；
Step5 compares the cool and thermal power load signal classification results of step Step4 and the load signal of step Step1, really
Determine recognition result.
2. long-term cool and thermal power load classification method in a kind of multi-energy system according to claim 1, which is characterized in that institute
State step Step3 specifically includes the following steps:
Step3-1 decomposes cool and thermal power load signal；
Step3-2, calculated load sample of signal entropy；
Step3-3 analyzes signal frequency domain details；
Step3-4 extracts Characteristic Entropy.
3. long-term cool and thermal power load classification method in a kind of multi-energy system according to claim 2, which is characterized in that institute
The Sample Entropy stated in Step3-2 step by step calculates step are as follows:
Step3-2-1 carries out coarse calculating to load signal；
Step3-2-2, changes obtained time series according to scale τ, and length N=L/ τ forms one group of m dimension arrow in order
Amount: from Yτ(1) Y is arrivedτ(N-m+1)；
Step3-2-3 defines Yτ(i) and YτThe distance between (j) for both difference maximum one in corresponding element, i.e.,
,
And calculate the corresponding d [Y of each i valueτ(i)-Yτ(j)]；
Step3-2-4, given threshold value r count d [Y for each 1≤i≤N-m+1τ(i)-Yτ(j)] less than r number and
This number and the ratio apart from total N-m, are denoted as
Step3-2-5 averages to all the points, is denoted as Cτ,m(r), i.e.,
Step3-2-6 increases dimension to m+1, repeats step Step3-2-2 to Step3-2-5, obtain Cτ,m+1(r)；
Step3-2-7 calculates Sample Entropy:
4. long-term cool and thermal power load classification method in a kind of multi-energy system according to claim 2, which is characterized in that institute
It states in Step3-4 step by step and extracts Characteristic Entropy the following steps are included: the entropy defined before three kinds of sudden load changes on scale increases speed
Degree is entropy gaining rate, is fitted to obtain slope using least square method, and combining has the Sample Entropy mean value composition of physical significance special
Sign amount (r1,r2)。
5. a kind of long-term cool and thermal power load classification method in multi-energy system described in any one of -4 according to claim 1,
It is characterized in that, support vector machines learner uses diameter to the algorithm that cool and thermal power load signal is classified in the step Step4
To base kernel function, classifier uses one-to-one algorithm, specifically includes the following steps:
Step4-1, to given sample set (xi,yi), i=1,2 ... n, xi∈Rd, y ∈ { -1,1 } is category label, by non-thread
Property transformationRd→Rn, input vector is mapped to n-dimensional space；
Step4-2 establishes hyperplane in higher dimensional space:
ω φ (X)+b=0 (2)
Wherein: weight
Step4-3, Optimal Separating Hyperplane optimization, i.e., in yi(ωφ(xi)+b) under >=1 constraint condition, classification plane Φ (ω)=| |
ω||2/ 2 obtain minimum value；
Step4-4 introduces Lagrange multiplier ai>=0, it is converted into Novel Algorithm:
It obtains optimal
Step4-5, optimal classification function are as follows:
Introduce kernel function K, K (Xi,Xj)=φ (Xi)·φ(Xj), then
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811319743.XA CN109214721A (en) | 2018-11-07 | 2018-11-07 | A kind of long-term cool and thermal power load classification method in multi-energy system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811319743.XA CN109214721A (en) | 2018-11-07 | 2018-11-07 | A kind of long-term cool and thermal power load classification method in multi-energy system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109214721A true CN109214721A (en) | 2019-01-15 |
Family
ID=64995362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811319743.XA Pending CN109214721A (en) | 2018-11-07 | 2018-11-07 | A kind of long-term cool and thermal power load classification method in multi-energy system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214721A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110032944A (en) * | 2019-03-20 | 2019-07-19 | 国网电力科学研究院(武汉)能效测评有限公司 | A kind of electric load feature extracting method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930347A (en) * | 2012-10-15 | 2013-02-13 | 河海大学 | Method for forecasting short term load under demand response |
| CN107907105A (en) * | 2017-10-26 | 2018-04-13 | 天津大学 | A kind of measuring method for organic Rankine bottoming cycle organic working medium gas-liquid two-phase flow pattern |
| CN108764265A (en) * | 2018-03-26 | 2018-11-06 | 海南电网有限责任公司电力科学研究院 | A kind of method for diagnosing faults based on algorithm of support vector machine |
-
2018
- 2018-11-07 CN CN201811319743.XA patent/CN109214721A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930347A (en) * | 2012-10-15 | 2013-02-13 | 河海大学 | Method for forecasting short term load under demand response |
| CN107907105A (en) * | 2017-10-26 | 2018-04-13 | 天津大学 | A kind of measuring method for organic Rankine bottoming cycle organic working medium gas-liquid two-phase flow pattern |
| CN108764265A (en) * | 2018-03-26 | 2018-11-06 | 海南电网有限责任公司电力科学研究院 | A kind of method for diagnosing faults based on algorithm of support vector machine |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110032944A (en) * | 2019-03-20 | 2019-07-19 | 国网电力科学研究院(武汉)能效测评有限公司 | A kind of electric load feature extracting method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Deep Learning Enhanced Solar Energy Forecasting with AI‐Driven IoT | |
| CN107274105B (en) | Linear discriminant analysis-based multi-attribute decision tree power grid stability margin evaluation method | |
| CN111428355B (en) | Modeling method for intelligent comprehensive statistics of power load numbers | |
| CN104881735A (en) | System and method of smart power grid big data mining for supporting smart city operation management | |
| CN109978404A (en) | Power transmission channel expansion planning method considering uncertainty factors and scene reduction | |
| CN107153845A (en) | A kind of isolated island detection method of the adaptive grid-connected photovoltaic system based on machine learning | |
| CN103440280A (en) | Retrieval method and device applied to massive spatial data retrieval | |
| CN109934456A (en) | A kind of method and system for acquisition operational system progress intelligent trouble detection | |
| CN105529714B (en) | Quick probability load flow calculation method based on normal distribution assemblage characteristic | |
| CN109272058A (en) | Integrated power load curve clustering method | |
| CN116824517A (en) | Substation operation and maintenance safety control system based on visualization | |
| CN109993359B (en) | Situation prediction method based on advanced machine learning | |
| CN110059938B (en) | Power distribution network planning method based on association rule driving | |
| CN109214721A (en) | A kind of long-term cool and thermal power load classification method in multi-energy system | |
| CN112784439B (en) | Energy internet planning method and device based on discretization model | |
| Hongzhan et al. | Comprehensive evaluation for transmission network planning scheme based on entropy weight method and VIKOR method | |
| CN112821456B (en) | Distributed source-storage-load matching method and device based on transfer learning | |
| CN115118015A (en) | Platform district power supply stability monitoring system based on fuse terminal | |
| Guo et al. | Time series forecasting based on deep extreme learning machine | |
| Zhang et al. | Research on railroad turnout fault diagnosis based on support vector machine | |
| Yang et al. | Ultra‐Short‐Term Multistep Prediction of Wind Power Based on Representative Unit Method | |
| CN113850422A (en) | Method for quickly searching transformer area line loss point based on multiple nonlinear regression or/and parallel vector | |
| Ramudu et al. | Siting and Sizing of DG for Loss Reduction and Voltage Sag Mitigation in RDS Using ABC Algorithm. | |
| Jiale | Research on application potential prediction method for urban energy system based on decision tree | |
| Li et al. | A Rapid Traffic Method of the Intelligent Connected Bus Based on Immune Algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |