CN112215472A - Clustering-based electric heating load response control method and device - Google Patents
Clustering-based electric heating load response control method and device Download PDFInfo
- Publication number
- CN112215472A CN112215472A CN202010984695.7A CN202010984695A CN112215472A CN 112215472 A CN112215472 A CN 112215472A CN 202010984695 A CN202010984695 A CN 202010984695A CN 112215472 A CN112215472 A CN 112215472A
- Authority
- CN
- China
- Prior art keywords
- clustering
- user
- load
- electric heating
- daily
- 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
- 238000005485 electric heating Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000004044 response Effects 0.000 title claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000003064 k means clustering Methods 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000005611 electricity Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000033228 biological regulation Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000005338 heat storage Methods 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an electric heating load response control method and device based on clustering, which comprises the following steps: clustering the daily loads of the users based on a clustering algorithm according to the historical data of the daily loads of the electric heating users to obtain a daily load clustering result of the users; and comparing the daily load clustering result of the user with the typical building type to obtain the building type corresponding to the user, and respectively carrying out response control on the load according to the building type. The invention can realize the user load characteristic identification at the aggregator end without additionally arranging additional metering equipment, thereby reducing the initial investment and being beneficial to the popularization of electric heating projects; by introducing a clustering algorithm, typical load characteristics of different loads can be obtained, adjustment strategies are respectively formulated according to fluctuation characteristics and adjustability of different user loads, the efficiency of user load adjustment is improved, and larger adjustment potential is released, so that the operation risk of the power grid is reduced.
Description
Technical Field
The invention relates to the technical field of power grid stabilization, in particular to an electric heating load response control method and device based on clustering.
Background
The rural areas in the northern China face the problem of serious heating pollution in winter, so measures such as 'coal to electricity' and 'electric energy substitution' are implemented to accelerate the improvement of clean heating proportion. However, the load of 'coal to electricity' is put into practice, so that the peak-valley difference of the power grid is increased, and the risk of the power grid and the electric heating equipment breaking down is increased. In addition, the problem of wind abandon in northern areas is serious, and the randomness and the fluctuation of wind power generation can also damage the power grid. Therefore, the problem of unstable power grid caused by the fluctuation of user electric heating load and new energy grid connection is solved, and the method is an important subject for realizing stable energy-saving electric heating.
In view of the above problems, Wang J, Lu N and the like have found that load shifting can be achieved without adding a dedicated heat storage device by the heat storage capacity of the household appliance, but the problem of grid instability is not sufficiently solved.
Therefore, some researchers coordinate the load side and the power generation side, and a load aggregator is used as a coordination center to make a control strategy, so that the new energy consumption can be promoted, and the stability of a power grid can be maintained. The aggregator contracts with the power supplier and the users respectively, establishes a relation between the power supplier and the electric heating users, and explores the demand response potential of the load through measures such as user resource reduction potential analysis, scheduling plan making in advance, excitation mechanism design and the like. Meanwhile, the heat storage equipment is adopted to adjust the electricity demand, and the coordination between the generated energy of the electricity supplier and the electric heating load of the user is realized.
In addition, some researchers regulate and control the user load by means of time-of-use electricity price and the like, and the load of the user can be promoted to be subjected to peak clipping and valley filling. However, the renewable energy consumption cannot be solved by simply adjusting from the user side without coordinating with the power supply side. Some researchers establish a combined operation mode of wind power and electric heating, and start coordination at the power generation side, so that the consumption of the wind power is greatly promoted, but targeted adjustment is not performed according to user side characteristics, and the maximization of benefits of all parties is not realized.
At present, when a load aggregator regulates and controls electric heating loads of users, different types of buildings adopt the same regulation mode, but the adjustable ranges of houses, office buildings and hospitals in actual life are different. For example, hospitals are relatively low in the adjustable range for the health of patients due to their particularity. Therefore, in order to uniformly regulate and control various building loads and give consideration to the comfort range of hospitals, the load regulation and control capability of load aggregators is reduced.
To achieve load identification and classification and targeted adjustment of user load, many researchers have proposed methods for user load analysis. The traditional load identification method is that an intelligent socket is installed in front of each electric appliance in an indoor to collect electricity utilization information, and the method needs to be invaded into a user for construction, so that inconvenience is brought to the user; the other type is that a load identification device is installed before each household power supply inlet wire to collect power utilization information, and space needs to be installed for the load identification device and a power supply needs to be accessed, so that management difficulty and purchasing cost can be increased. Patent CN105974220A proposes a residential community electrical load recognition system, which is configured to determine the usage of residential electrical load by setting a monitoring management module and a first communication module at the main server side of the residential community and setting a load electrical load recognition module and a second communication module at the user side, so as to monitor the load devices of users in the whole residential community. However, this method of identifying the electrical load requires installation of multiple modules at the user side and the general service side, and cannot be implemented in rural areas.
In view of the above research situation, the current load regulation for heat accumulating type electric heating has the following two problems:
1. when the heating load of a user is measured, a complex measuring device is mostly needed, and measuring equipment needs to be additionally installed on the user side, so that extra cost is brought to load regulation and control. For rural areas, it is often difficult to install such load detection devices.
2. At present, when the electric heating load of a user is adjusted, the same adjusting and controlling mode is usually adopted for different types of loads, but the load characteristics and the adjusting capacity of different buildings are different, and the load is difficult to be adjusted in a targeted manner in the prior art.
Based on the above current research situation, there is a need to provide a method for measuring and classifying the user load without additionally installing a device for measuring the user heat load on the user side.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a cluster-based electric heating load response control method and device, and solves the problem that a user heat load measuring device needs to be additionally installed on a user side in electric heating load control.
In order to achieve the above purpose, the invention adopts the following technical scheme: a cluster-based electric heating load response control method comprises the following steps:
clustering the daily loads of the users according to the historical data of the daily loads of the electric heating users to obtain a daily load clustering result of the users;
and comparing the daily load clustering result of the user with the typical building type to obtain the building type corresponding to the user, and respectively carrying out response control on the load according to the building type.
Further, the algorithm adopted by the clustering includes: k-means, K-medoids or Clara clustering algorithms.
Further, based on a K-means clustering algorithm, the user daily load clustering method comprises the following steps:
1) setting a clustering center number K;
2) randomly generating K groups of user daily load data in the variation range of the clustered user daily load data as a clustering center of the cluster, and recording as: c1(1),C1(2),…,C1(K);
3) Distributing the user daily load data to the nearest clustering center according to the Euclidean distance from the daily load curve to the clustering center, and forming K user daily load data groups of different categories;
4) taking the mean value of the daily load data of all users in each user daily load data group as a new clustering center value, wherein the clustering center is updated as follows: c2(1),C2(2),…,C2(K);
5) And repeating the steps 3) and 4), redistributing the daily load data of the user to the clustering center with the minimum Euclidean distance to form a new daily load data group of the user, and updating the clustering center until the clustering result is not changed to obtain K clustering results.
Further, the typical building types include: hospitals, residences, office buildings, shopping malls, and hotels.
An electric heating load response control device based on clustering comprises:
the clustering module is used for clustering the daily loads of the users according to the historical data of the daily loads of the electric heating users to obtain a user daily load clustering result;
and the response control module is used for comparing the user daily load clustering result with the typical building type to obtain the building type corresponding to the user, and respectively performing response control on the load according to the building type.
Further, the algorithm adopted by the clustering includes: k-means, K-medoids or Clara clustering algorithms.
Further, based on a K-means clustering algorithm, the user daily load clustering method comprises the following steps:
1) setting a clustering center number K;
2) randomly generating K groups of user daily load data in the variation range of the clustered user daily load data as a clustering center of the cluster, and recording as: c1(1),C1(2),…,C1(K);
3) Distributing the user daily load data to the nearest clustering center according to the Euclidean distance from the daily load curve to the clustering center, and forming K user daily load data groups of different categories;
4) taking the mean value of the daily load data of all users in each user daily load data group as a new clustering center value, wherein the clustering center is updated as follows: c2(1),C2(2),…,C2(K);
5) And repeating the steps 3) and 4), redistributing the daily load data of the user to the clustering center with the minimum Euclidean distance to form a new daily load data group of the user, and updating the clustering center until the clustering result is not changed to obtain K clustering results.
Further, the typical building types include: hospitals, residences, office buildings, shopping malls, and hotels.
The invention achieves the following beneficial effects:
1. through calculation and classification of user loads, the electric heating reconstruction project implemented in rural areas can realize user load characteristic identification at a aggregator end without additionally arranging additional metering equipment, so that initial investment is reduced, and popularization of the electric heating project is facilitated;
2. by introducing a clustering algorithm, typical load characteristics of different medium loads can be obtained, adjustment strategies are respectively formulated according to fluctuation characteristics and adjustability of different user loads, the efficiency of user load adjustment is improved, and larger adjustment potential is released, so that the operation risk of the power grid is reduced.
Drawings
FIG. 1 is a flow chart of user load clustering in an embodiment of the present invention;
fig. 2 is a flowchart of an electric heating load response control method in the embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Clustering is an important method for data processing, and data can be grouped according to the selected characteristics and the group number selected manually or the group number generated by clustering, so that the effects that data among groups are different as much as possible and data in the groups are similar as much as possible are achieved. The method comprises the steps of clustering electric heating user loads, namely classifying daily heat load curves of users according to fluctuation conditions, change trends and load sizes of the users, classifying the daily heat load curves into several classes according to user load change characteristics, and making corresponding regulation strategies according to the several classes of typical loads, so that the regulation effect on heat accumulating type electric heating is improved, the stability of a power grid is maintained, and the new energy consumption effect is increased.
In order to realize the planning and coordination of the electric heating load, the method adopts a clustering algorithm, and the load of the electric heating users is divided into a plurality of categories according to the load fluctuation condition of the electric heating users, such as: office buildings, hospitals and houses, and then load aggregators coordinate different means according to different types of users.
Example 1:
as shown in fig. 1 and 2, an electric heating load response control method based on a clustering method includes the steps of:
step 1, clustering user daily loads based on a clustering algorithm according to historical data of daily loads of electric heating users to obtain a user daily load clustering result;
the user daily load clustering method comprises the following steps: including but not limited to K-means, K-medoids, and Clara, among others.
Taking the K-means algorithm as an example, the user load clustering steps are as follows:
1) the clustering center number K (i.e., the number of categories of the user daily load) is set.
2) Randomly generating K groups of user daily load data in the variation range of the clustered user daily load data as a clustering center of the cluster, and recording as: c1(1),C1(2),…,C1(K)。
3) And distributing the user daily load data to the nearest clustering center according to the Euclidean distance from the daily load curve to the clustering center, and forming K user daily load data groups of different categories.
The calculation formula of the Euclidean distance is as follows:
wherein X is daily load data of a clustering center, Y is daily load data of a user to be clustered, and XiI time day load data, y for the clustering centeriThe load data of the users to be clustered are the load data of the users at the moment i, and n is the time number of the load data of the users.
4) Taking the mean value of daily load data of all users in each user group as a new clustering center value, wherein the clustering center is updated as follows: c2(1),C2(2),…,C2(K)。
5) And repeating the steps 3) and 4), redistributing the daily load data of the user to the clustering center with the minimum Euclidean distance to form a new user data group, and updating the clustering center until the clustering result is not changed to obtain K clustering results.
Through the process, the user daily load is clustered to obtain K clustering centers and corresponding K groups of data, the data of the clustering centers are used as typical user loads, and the user daily loads are divided into K types.
Step 2, comparing the user daily load clustering result with a typical building type to obtain a building type corresponding to the user, classifying buildings in a heat supply area according to the building type, and realizing targeted load response control:
typical building types include: hospitals, houses, office buildings and the like can be subdivided into night office buildings, day office buildings, night houses and day houses, under the general condition, the office buildings are large in electricity consumption in the daytime, the electricity consumption at night is small, the houses are small in electricity consumption in the daytime, the electricity consumption at night is large, and the houses can be subdivided according to the actual conditions.
Different buildings can respond to different load adjusting intervals, and the load of different buildings is reduced in a pertinence manner at the aggregator side according to the building type and the load adjusting interval of each building type.
The amount of the adjustable load of different buildings is different, taking a heat supply area including hospitals, office buildings and houses as an example, the office buildings ensure comfortable working environment, and the load adjustable interval is lower than that of the residential buildings; the hospital is lower than office buildings in the load adjustable interval for ensuring the health of patients.
The load adjustable intervals of hospitals, office buildings and houses are respectively +/-10%, +/-30% and +/-40%. When the clustering method is not added, the method is limited by the adjustable interval of hospital buildings, and the adjustment range of the area is only +/-10%. After the clustering method is added, the pertinence adjustment can be carried out on different buildings, so that the adjustment range of office buildings and residential buildings is enlarged, and larger load reduction can be obtained in the whole area. The load of the power grid can be effectively reduced in the peak period of power utilization, and the stability and the safety of the power grid are improved.
The types of buildings included in the heating area include, but are not limited to, hospital, office building, house, and the like, and may also include shopping mall, hotel, and the like. The load response control method is characterized in that buildings with different load adjustable intervals are distinguished to realize targeted adjustment.
Example 2:
an electric heating load response control device based on clustering comprises:
the clustering module is used for clustering the daily loads of the users based on a clustering algorithm according to the historical data of the daily loads of the electric heating users to obtain a daily load clustering result of the users;
and the response control module is used for comparing the user daily load clustering result with the typical building type to obtain the building type corresponding to the user, and respectively performing response control on the load according to the building type.
Further, the clustering algorithm includes: k-means, K-medoids and Clara clustering algorithms.
Further, based on a K-means clustering algorithm, the user daily load clustering method comprises the following steps:
1) setting a clustering center number K;
2) randomly generating K groups of user daily load data in the variation range of the clustered user daily load data as a clustering center of the cluster, and recording as: c1(1),C1(2),…,C1(K);
3) Distributing the user daily load data to the nearest clustering center according to the Euclidean distance from the daily load curve to the clustering center, and forming K user daily load data groups of different categories;
4) taking the mean value of the daily load data of all users in each user daily load data group as a new clustering center value, wherein the clustering center is updated as follows: c2(1),C2(2),…,C2(K);
5) And repeating the steps 3) and 4), redistributing the daily load data of the user to the clustering center with the minimum Euclidean distance to form a new daily load data group of the user, and updating the clustering center until the clustering result is not changed to obtain K clustering results.
Further, the typical building types include: hospitals, residences, office buildings, shopping malls, and hotels.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (8)
1. A cluster-based electric heating load response control method is characterized in that: the method comprises the following steps:
clustering the daily loads of the users according to the historical data of the daily loads of the electric heating users to obtain a daily load clustering result of the users;
and comparing the daily load clustering result of the user with the typical building type to obtain the building type corresponding to the user, and respectively carrying out response control on the load according to the building type.
2. The cluster-based electric heating load response control method according to claim 1, wherein the cluster-based electric heating load response control method comprises the following steps: the algorithm adopted by the clustering comprises the following steps: k-means, K-medoids or Clara clustering algorithms.
3. The cluster-based electric heating load response control method according to claim 2, wherein the cluster-based electric heating load response control method comprises the following steps: based on a K-means clustering algorithm, the user daily load clustering method comprises the following steps:
1) setting a clustering center number K;
2) randomly generating K groups of user daily load data in the variation range of the clustered user daily load data as a clustering center of the cluster, and recording as: c1(1),C1(2),…,C1(K);
3) Distributing the user daily load data to the nearest clustering center according to the Euclidean distance from the daily load curve to the clustering center, and forming K user daily load data groups of different categories;
4) taking the mean value of the daily load data of all users in each user daily load data group as a new clustering center value, wherein the clustering center is updated as follows: c2(1),C2(2),…,C2(K);
5) And repeating the steps 3) and 4), redistributing the daily load data of the user to the clustering center with the minimum Euclidean distance to form a new daily load data group of the user, and updating the clustering center until the clustering result is not changed to obtain K clustering results.
4. The cluster-based electric heating load response control method according to claim 1, wherein the cluster-based electric heating load response control method comprises the following steps: the typical building types include: hospitals, residences, office buildings, shopping malls, and hotels.
5. An electric heating load response control device based on clustering is characterized in that: the method comprises the following steps:
the clustering module is used for clustering the daily loads of the users according to the historical data of the daily loads of the electric heating users to obtain a user daily load clustering result;
and the response control module is used for comparing the user daily load clustering result with the typical building type to obtain the building type corresponding to the user, and respectively performing response control on the load according to the building type.
6. The cluster-based electric heating load response control device of claim 5, wherein: the algorithm adopted by the clustering comprises the following steps: k-means, K-medoids or Clara clustering algorithms.
7. The cluster-based electric heating load response control device of claim 6, wherein: based on a K-means clustering algorithm, the user daily load clustering method comprises the following steps:
1) setting a clustering center number K;
2) randomly generating K groups of user daily load data in the variation range of the clustered user daily load data as a clustering center of the cluster, and recording as: c1(1),C1(2),…,C1(K);
3) Distributing the user daily load data to the nearest clustering center according to the Euclidean distance from the daily load curve to the clustering center, and forming K user daily load data groups of different categories;
4) taking the mean value of the daily load data of all users in each user daily load data group as a new clustering center value, wherein the clustering center is updated as follows: c2(1),C2(2),…,C2(K);
5) And repeating the steps 3) and 4), redistributing the daily load data of the user to the clustering center with the minimum Euclidean distance to form a new daily load data group of the user, and updating the clustering center until the clustering result is not changed to obtain K clustering results.
8. The cluster-based electric heating load response control device of claim 5, wherein: the typical building types include: hospitals, residences, office buildings, shopping malls, and hotels.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010984695.7A CN112215472A (en) | 2020-09-18 | 2020-09-18 | Clustering-based electric heating load response control method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010984695.7A CN112215472A (en) | 2020-09-18 | 2020-09-18 | Clustering-based electric heating load response control method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112215472A true CN112215472A (en) | 2021-01-12 |
Family
ID=74050523
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010984695.7A Pending CN112215472A (en) | 2020-09-18 | 2020-09-18 | Clustering-based electric heating load response control method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112215472A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112884358A (en) * | 2021-03-16 | 2021-06-01 | 国网河北省电力有限公司电力科学研究院 | Electric heating equipment ordered power utilization optimized scheduling method and terminal |
CN117272121A (en) * | 2023-11-21 | 2023-12-22 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105719194A (en) * | 2016-01-11 | 2016-06-29 | 河南许继仪表有限公司 | Automatic optimization type power load classification method |
CN106408008A (en) * | 2016-09-08 | 2017-02-15 | 国网江西省电力公司赣州供电分公司 | Load curve distance and shape-based load classification method |
CN111612273A (en) * | 2020-05-28 | 2020-09-01 | 山东大学 | Regional-level comprehensive energy system partition design method and system |
-
2020
- 2020-09-18 CN CN202010984695.7A patent/CN112215472A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105719194A (en) * | 2016-01-11 | 2016-06-29 | 河南许继仪表有限公司 | Automatic optimization type power load classification method |
CN106408008A (en) * | 2016-09-08 | 2017-02-15 | 国网江西省电力公司赣州供电分公司 | Load curve distance and shape-based load classification method |
CN111612273A (en) * | 2020-05-28 | 2020-09-01 | 山东大学 | Regional-level comprehensive energy system partition design method and system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112884358A (en) * | 2021-03-16 | 2021-06-01 | 国网河北省电力有限公司电力科学研究院 | Electric heating equipment ordered power utilization optimized scheduling method and terminal |
CN112884358B (en) * | 2021-03-16 | 2023-01-24 | 国网河北省电力有限公司电力科学研究院 | Electric heating equipment ordered power utilization optimized scheduling method and terminal |
CN117272121A (en) * | 2023-11-21 | 2023-12-22 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
CN117272121B (en) * | 2023-11-21 | 2024-03-12 | 江苏米特物联网科技有限公司 | Hotel load influence factor quantitative analysis method based on Deep SHAP |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9069337B2 (en) | System and method for estimating and providing dispatchable operating reserve energy capacity through use of active load management | |
KR20140105506A (en) | Adaptation of a power generation capacity and determining of an energy storage unit size | |
WO2022193794A1 (en) | Multi-objective energy management method for smart community microgrid that takes into consideration decommissioned batteries | |
CN110109971A (en) | A kind of low-voltage platform area user power utilization Load Characteristic Analysis method | |
CN112215472A (en) | Clustering-based electric heating load response control method and device | |
KR101544463B1 (en) | A control method for controlling energy of building based ob microgrid and system for same | |
CN110503461B (en) | Demand response method based on residential user clustering in smart power grid | |
CN112413702B (en) | Method and system for matching heat accumulating type electric heating load with distribution network area | |
CN112581012A (en) | Electricity customer classification method participating in demand response | |
CN113988471A (en) | Multi-objective optimization method for micro-grid operation | |
CN106685313A (en) | Power generation control method and device for photovoltaic power station and photovoltaic power station | |
CN114530877A (en) | Distributed photovoltaic absorption method for power distribution network | |
CN113746105A (en) | Optimal control method, device, equipment and storage medium for power demand response | |
CN206370695U (en) | A kind of photovoltaic plant | |
CN113258583A (en) | Power utilization optimization method for transformer area side load | |
Gong et al. | Analysis of electricity consumption behavior of air conditioning based on the perspective of power demand response | |
Joseph et al. | Demand response program for smart grid through real time pricing and home energy management system | |
CN105184408A (en) | Energy-saving method based on electrical appliance electricity utilization effectiveness grading and user electricity utilization behavior recognition | |
CN111102644A (en) | Method and system for determining potential of heat accumulating type electric heating participating in power grid peak shaving | |
Dai et al. | A demand response scheme in smart grid with clustering of residential customers | |
CN115864531A (en) | Monitoring system and method for carbon emission of regional distributed photovoltaic power generation | |
CN112113316B (en) | Method for extracting air conditioner load | |
CN114580757A (en) | Load response prediction method and system based on industry type of large power consumption user | |
CN115271168A (en) | Method and device for predicting response potential of electrical load and storage medium | |
CN111222079A (en) | Electric power prediction method, device, storage medium and processor |
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: 20210112 |