CN108767847A - A kind of non-intrusion type power load decomposition method and device - Google Patents
A kind of non-intrusion type power load decomposition method and device Download PDFInfo
- Publication number
- CN108767847A CN108767847A CN201810398300.8A CN201810398300A CN108767847A CN 108767847 A CN108767847 A CN 108767847A CN 201810398300 A CN201810398300 A CN 201810398300A CN 108767847 A CN108767847 A CN 108767847A
- Authority
- CN
- China
- Prior art keywords
- load
- type power
- intrusion type
- equipment
- power load
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a kind of non-intrusion type power load decomposition method, this method includes：Obtain the load profile library of electrical equipment and total load data to be decomposed；According to load profile library, the model that HMM is combined with FHMM is established；The total load data to be measured are decomposed by special algorithm.The present invention considers the correlation between equipment so that the accuracy of home electrical load decomposition is improved advantage.
Description
Technical field
The present invention relates to technical field of electric power, more particularly to a kind of non-intrusion type power load decomposition method and device.
Background technology
Currently, many countries are dedicated to reducing power consumption so that the energy is efficiently utilized, and realizes holding for the energy
Supervention exhibition.We must find technical solution and be used to reduce and optimize the energy.For owner and resident family, this mesh is realized
Calibration method is the power consumption that load monitoring technology monitors them.
Load monitoring technology is divided into intrusive load monitoring and non-intrusion type load monitoring and decomposes.Intrusive load monitoring
It needs to be equipped with the sensor with communication function for each electrical equipment, telecommunications is used by what sensor acquired each electrical equipment
It ceases to analyze user power utilization behavior；Non-intrusion type load monitoring only needs to install a sensing in user power utilization inlet with decomposition
Device acquires the power information of electricity consumption inlet to monitor the electricity consumption situation and working condition of each electrical equipment, to understand use
Family electricity consumption rule and energy consumption.Due to non-intrusion type method have small investment, it is easy for installation, using it is simple the features such as, because
And practical application is stronger.
Non-intrusion type load monitoring technology based on HMM is also one of common method of load monitoring.There are many HMM models
Deformation, such as FHMM, CFHMM, DHMM.Existing mainly concentrated with the relevant patent of HMM load decompositions carries out HMM model
The HMM model of deformation or several deformations is combined to obtain a kind of new model and is used for load decomposition.HMM model be about when
The probabilistic model of sequence, description are generated unobservable state random sequence, i.e. state by a hiding Markov chain at random
Sequence (state sequence), then observation random sequence, i.e. observation sequence are generated by one observation of each state generation
The process of (observation sequence).
Present home electrical load decomposition technology always assumed that when being modeled based on FHMM each equipment it
Between be independent from each other, be not generate any contact each other.But it is tool between each housed device in real life
Relevant property, for example, at home Play Station games when need television on machine, etc..
Invention content
Technical problem to be solved by the present invention lies in the deficiencies for overcoming the above-mentioned prior art, provide a kind of non-intrusion type use
Electric load decomposition method, this method include：
Obtain the load profile library of electrical equipment and total load data to be measured；
According to load profile library, the model that HMM is combined with FHMM is established；
The total load data to be measured are decomposed by special algorithm.
Preferably, the load profile library is the electric parameter data according to the electrical equipment under steady-state operating condition
Collection is established.
Preferably, the load characteristic is load steady-state current.
Preferably, the special algorithm is viterbi algorithm.
Preferably, the load characteristic include each equipment probability-distribution function, equipment state and equipment between that
This correlation.
A kind of non-intrusion type power load decomposer, the device include：
Acquisition module, the load profile library for obtaining each electrical equipment and total load data to be measured；
Model building module establishes what HMM was combined with FHMM for obtaining voice messaging according to load profile library
Model；
Decomposing module, for being decomposed to the total load data to be measured by special algorithm.
Preferably, the load characteristic is load steady-state current.
Preferably, the special algorithm is viterbi algorithm.
Preferably, the load profile library is the electric parameter data according to the electrical equipment under steady-state operating condition
Collection is established.
Preferably, the load characteristic include each equipment probability-distribution function, equipment state and equipment between that
This correlation.
Have compared with prior art according to a kind of non-intrusion type power load decomposition method provided by the invention and device
Following advantage：
1) present invention realizes the load decomposition of electric load at steady state, and decomposition result is fed back to user,
It can be energy saving；Especially home electrical load.
2) what the present invention chose is the electric current of electrical equipment at steady state as electric parameter, data used under low frequency
It can directly be collected by intelligent electric meter general on current market, reduce hardware cost input.
3) present invention considers the correlation between equipment so that the accuracy that electric load decomposes is improved.
Description of the drawings
Fig. 1 is the work flow diagram of the present invention,
Fig. 2 is the power information acquisition system structure chart of the present invention,
Fig. 3 is the illustraton of model that the HMM of the present invention is combined with FHMM,
Fig. 4 is the structure chart of the present invention.
Specific implementation mode
Clearly to illustrate the scheme in the present invention, preferred embodiment is given below and being described with reference to the accompanying drawings.With
Under illustrative in nature on be only exemplary and be not intended to limitation the disclosure application or purposes.It should be understood that
In whole attached drawings, corresponding reference numeral indicates identical or corresponding component and feature.
As shown in Figure 1.A kind of non-intrusion type power load decomposition method, this method include：
S101 obtains the load profile library of electrical equipment and total load data to be measured；The load profile
Library is established according to the electric parameter data set of the electrical equipment under steady-state operating condition.Since the fluctuation situation of load current is bright
Judge that electrical appliance type and working condition are more accurate when showing smaller than active power, and using load steady-state current as load characteristic
Really, accuracy rate higher is decomposed.So the present invention is using load steady-state current as load characteristic.Electrical equipment is negative in order to obtain
Lotus data, the decomposition algorithm for facilitating verification to propose, have built a set of electricity consumption for non-intrusion type load decomposition research in experiment
Information acquisition system, detailed data-gathering process are as shown in Figure 2.
The load characteristic include each equipment probability-distribution function, equipment state and equipment between mutual correlation
Property.First, the probability-distribution function of electric current is obtained by current data collection；Secondly, by the peak value of probability distribution, each use is obtained
The status number of electric equipment.The current value for peak value occur can consider as a state.Finally, equipment is obtained according to Pearson came formula
Between correlation.
Pearson came formula
N：The number of electrical equipment；
Electrical equipment i is in state value in t moment；
Electrical equipment j is in state value in t moment；
State average values of the electrical equipment i at each moment；
State average values of the electrical equipment i at each moment；
State average values of the electrical equipment j at each moment；
S102 establishes the model that HMM is combined with FHMM according to load profile library；
By equipment be divided into it is relevant with it is incoherent, the model of HMM is established to relevant device, to incoherent equipment establish
The model of FHMM, it is assumed that equipment 1 is to be mutually related with equipment 2, and model is as shown in Figure 3.
S103 decomposes the total load data to be measured by special algorithm.The special algorithm is Viterbi
(Viterbi) algorithm.
After the invention, do not have an impact human-computer interaction, and system is allowed to seem more humane, safer.
As shown in Figure 4.A kind of non-intrusion type power load decomposer, the device include：
Acquisition module 201, the load profile library for obtaining each electrical equipment and total load data to be measured；It is described
Load characteristic is load steady-state current.The load profile library is according to the electrical of the electrical equipment under steady-state operating condition
Parameter data set is established.
Model building module 202 is established HMM and FHMM phases and is tied for obtaining voice messaging according to load profile library
The model of conjunction；The load characteristic include each equipment probability-distribution function, equipment state and equipment between mutual phase
Guan Xing.
Decomposing module 203, for being decomposed to the total load data to be measured by special algorithm.The specific calculation
Method is viterbi algorithm.
In conclusion above said content is only the embodiment of the present invention, it is merely to illustrate the principle of the present invention, is not used
In restriction protection scope of the present invention.All within the spirits and principles of the present invention, any modification made by, changes equivalent replacement
Into etc., it should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of non-intrusion type power load decomposition method, which is characterized in that this method includes：
Obtain the load profile library of electrical equipment and total load data to be decomposed；
According to load profile library, the model that HMM is combined with FHMM is established；
The total load data to be measured are decomposed by special algorithm.
2. non-intrusion type power load decomposition method as described in claim 1, it is characterised in that：The load profile library
It is to be established according to the electric parameter data set of the electrical equipment under steady-state operating condition.
3. non-intrusion type power load decomposition method as described in claim 1, it is characterised in that：The load characteristic is load
Steady-state current.
4. non-intrusion type power load decomposition method as described in claim 1, it is characterised in that：The special algorithm is Wei Te
Compare algorithm.
5. non-intrusion type power load decomposition method as described in claim 1, it is characterised in that：The load characteristic includes each
A equipment probability-distribution function, equipment state and equipment between mutual correlation.
6. a kind of non-intrusion type power load decomposer, it is characterised in that：The device includes：
Acquisition module, the load profile library for obtaining each electrical equipment and total load data to be measured；
Model building module establishes the mould that HMM is combined with FHMM for obtaining voice messaging according to load profile library
Type；
Decomposing module, for being decomposed to the total load data to be measured by special algorithm.
7. non-intrusion type power load decomposer as claimed in claim 6, it is characterised in that：The load characteristic is load
Steady-state current.
8. non-intrusion type power load decomposer as claimed in claim 6, it is characterised in that：The special algorithm is Wei Te
Compare algorithm.
9. non-intrusion type power load decomposer as claimed in claim 6, it is characterised in that：The load profile library
It is to be established according to the electric parameter data set of the electrical equipment under steady-state operating condition.
10. non-intrusion type power load decomposer as claimed in claim 6, it is characterised in that：The load characteristic includes
Each equipment probability-distribution function, equipment state and equipment between mutual correlation.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810107002 | 2018-02-02 | ||
| CN2018101070029 | 2018-02-02 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108767847A true CN108767847A (en) | 2018-11-06 |
| CN108767847B CN108767847B (en) | 2020-09-01 |
Family
ID=64012118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810398300.8A Active CN108767847B (en) | 2018-02-02 | 2018-04-28 | Non-invasive electric load decomposition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108767847B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109495355A (en) * | 2018-11-15 | 2019-03-19 | 长沙理工大学 | Intelligent household energy router |
| CN109685552A (en) * | 2018-12-06 | 2019-04-26 | 国网山东省电力公司青岛供电公司 | The analysis of non-intrusion type residential electricity consumption efficiency and method of servicing |
| CN113627661A (en) * | 2021-08-02 | 2021-11-09 | 深圳供电局有限公司 | Method for predicting charging load of electric automobile |
| CN116051910A (en) * | 2023-03-10 | 2023-05-02 | 深圳曼顿科技有限公司 | Non-invasive load identification method, device, terminal equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103001230A (en) * | 2012-11-16 | 2013-03-27 | 天津大学 | Non-invasive power load monitoring and decomposing current mode matching method |
| CN105514993A (en) * | 2015-12-17 | 2016-04-20 | 华电智连信达科技（北京）有限公司 | Power load decomposition method and power load decomposition device |
| CN107085764A (en) * | 2017-04-12 | 2017-08-22 | 西安交通大学 | A kind of load decomposition method and device based on improvement DFHMM models |
-
2018
- 2018-04-28 CN CN201810398300.8A patent/CN108767847B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103001230A (en) * | 2012-11-16 | 2013-03-27 | 天津大学 | Non-invasive power load monitoring and decomposing current mode matching method |
| CN105514993A (en) * | 2015-12-17 | 2016-04-20 | 华电智连信达科技（北京）有限公司 | Power load decomposition method and power load decomposition device |
| CN107085764A (en) * | 2017-04-12 | 2017-08-22 | 西安交通大学 | A kind of load decomposition method and device based on improvement DFHMM models |
Non-Patent Citations (5)
| Title |
|---|
| DOMINIK EGARTER等: "PALDi: Online Load Disaggregation via Particle Filtering", 《IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT》 * |
| 周晨轶，等: "基于差分进化算法的居民用电负荷分解方法", 《南方电网技术》 * |
| 岳德君: "时间序列数据流中相关性分析技术的研究", 《中国优秀所示学位论文全文数据库 信息科技辑》 * |
| 张玲玲: "基于HSMM的非侵入式家庭电力负荷分解算法研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 陈思运，等: "基于因子隐马尔可夫模型的负荷分解方法及灵敏度分析", 《电力系统自动化》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109495355A (en) * | 2018-11-15 | 2019-03-19 | 长沙理工大学 | Intelligent household energy router |
| CN109685552A (en) * | 2018-12-06 | 2019-04-26 | 国网山东省电力公司青岛供电公司 | The analysis of non-intrusion type residential electricity consumption efficiency and method of servicing |
| CN113627661A (en) * | 2021-08-02 | 2021-11-09 | 深圳供电局有限公司 | Method for predicting charging load of electric automobile |
| CN116051910A (en) * | 2023-03-10 | 2023-05-02 | 深圳曼顿科技有限公司 | Non-invasive load identification method, device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108767847B (en) | 2020-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108767847A (en) | A kind of non-intrusion type power load decomposition method and device | |
| CN111428816B (en) | Non-invasive load decomposition method | |
| CN115663312B (en) | Battery operation monitoring system and method based on battery protection | |
| Huang et al. | False data injection attacks detection in smart grid: A structural sparse matrix separation method | |
| CN116632983B (en) | Charging and discharging control system suitable for outdoor energy storage power supply | |
| CN105186693A (en) | Non-invasive electrical load identification system and method | |
| CN106655160A (en) | Non-intrusion electric power load decomposition identification decision method and system | |
| Tripathi et al. | Dynamic prediction of powerline frequency for wide area monitoring and control | |
| Cloth et al. | Computing battery lifetime distributions | |
| CN104331846A (en) | Multi-source modeling and collaborative analysis method for electricity stealing behavior | |
| CN103018611B (en) | Non-invasive load monitoring method and system based on current decomposition | |
| CN112241925A (en) | Non-invasive load decomposition method and system | |
| CN110929115B (en) | Power utilization safety monitoring method and system based on power utilization characteristics | |
| US20170059634A1 (en) | Power monitoring system and method for monitoring power thereof | |
| Kommey et al. | An artificial intelligence‐based non‐intrusive load monitoring of energy consumption in an electrical energy system using a modified K‐Nearest Neighbour algorithm | |
| CN102072976A (en) | Method and system for identifying electrical appliance state | |
| CN103648116B (en) | The power consumption wireless sensor network optimized approach analyzed based on program | |
| Jin et al. | Battery optimal scheduling based on energy balance in wireless sensor networks | |
| CN109490622B (en) | Electric quantity data verification technology based on tri-state information | |
| Mei et al. | Random forest based adaptive non-intrusive load identification | |
| CN116307886A (en) | Method and device for monitoring production state of enterprise in real time | |
| CN116009680A (en) | Energy consumption tracing method, storage medium and equipment based on data center energy saving system | |
| CN115034472A (en) | Distributed photovoltaic operation intelligent prediction management system | |
| CN115293265A (en) | Non-invasive monitoring method and system for building electricity utilization | |
| CN113033076A (en) | Non-invasive load monitoring method and device based on multi-chain decomposition method |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210326 Address after: 010000 No.1, wutasi East Street, Yuquan District, Hohhot, Inner Mongolia Autonomous Region Patentee after: INNER MONGOLIA POWER GROUP SYNTHESIS ENERGY Co.,Ltd. Address before: 212200 Daquan Road, Xinba Town, Yangzhong City, Zhenjiang City, Jiangsu Province Patentee before: YANGZHONG INTELLIGENT ELECTRICAL INSTITUTE, NORTH CHINA ELECTRIC POWER University |