CN109002930A - A kind of home energy source Internet of Things Demand Side Response control method neural network based - Google Patents
A kind of home energy source Internet of Things Demand Side Response control method neural network based Download PDFInfo
- Publication number
- CN109002930A CN109002930A CN201810950629.0A CN201810950629A CN109002930A CN 109002930 A CN109002930 A CN 109002930A CN 201810950629 A CN201810950629 A CN 201810950629A CN 109002930 A CN109002930 A CN 109002930A
- Authority
- CN
- China
- Prior art keywords
- neural network
- demand side
- side response
- strategy
- energy source
- 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
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a kind of home energy source Internet of Things Demand Side Response control methods neural network based, it includes the following steps: (1) using intelligent electric meter to household electricity equipment progress real-time data acquisition and using collected data as electricity consumption sample;Step 2, neural network algorithm module are trained according to electricity consumption sample, load curtailment strategy and Energy Saving Strategy when generating habit predicted value, switch probability and the weight coefficient of user power utilization and generating the response of household demand side according to habit predicted value, switch probability and weight coefficient;Step 3, control module are automatically controlled according to load curtailment strategy and Energy Saving Strategy realizes Demand Side Response movement;It for the needs of wired home Internet of Things, realizes that dynamic manages, selects dependence low user, automatization level is high, and advantageous user's good experience can be with overcome the deficiencies in the prior art.
Description
Technical field
The invention belongs to electrical and field of automation technology more particularly to a kind of home energy source Internet of Things neural network based
Net Demand Side Response control method.
Background technique:
Demand response (Demand Response, abbreviation DR) the i.e. abbreviation of electricity needs response refers to when wholesale power market valence
When lattice increase or system reliability is compromised, the inductivity that power consumer receives supplier of electricity sending reduces the direct compensation of load
After notice or power price rising signals, changes its intrinsic habit power mode, reach reduction or elapse certain period
Power load and respond power supply, to ensure the stabilization of power grids, and the acts and efforts for expediency for inhibiting electricity price to rise.It is demand side pipe
Manage one of the solution of (DSM).
Current needs side responds main project implementation or experimental city, province are implemented.Since 2014, Tangshan City has been removed
Outside, Beijing, Shanghai, Foshan San Shi and Jiangsu Province successfully implement Demand Side Response project several times, and substantially annual summer is real
Apply one twice.Wherein Jiangsu Province's Demand Side Response is in domestically leading level from the point of view of practical range, response capacity.2017
July, Jiangsu Province was believed that tissue provincial electric power company of committee starts real-time automatic demand response to Zhangjiagang bonded area, metallurgical garden, not
Under the premise of influence enterprise normally produces, only it is the electricity needs for reducing 55.8 ten thousand kilowatts in garden with 1 seconds, creates
International precedent.
But there is also some problems in pilot operational process, such as: 1. current users participate in the motivation of demand response simultaneously
Price signal or motivator, but single financial subsidies (100 yuan every kilowatt or so) are not come from, once subsidy stops,
Corresponding project of implementing is with regard to hard to carry on;2. the object of current pilot is mainly industrial user, and work out a scheme factor there are one,
It is small, interactive not strong to participate in scope of subject.3. the price differential of time-of-use tariffs is not big enough, can not due to lacking real-time and tou power price
It is attracted to the Demand-sides resource such as most potential energy storage.
Chinese patent CN201510007856.6 discloses a kind of family's workload demand side response implementation method, purpose purport
It is relatively simple to meet type in solution domestic consumer, and should not automatically control, the problem more slow to Demand Side Response speed.
The main implementation method of the invention is to install two-dimension code generator additional on household appliances, to monitor switch state, when two dimensional code is raw
It grows up to be a useful person and monitors that electric switch variation just generates two dimensional code, content includes the information such as user information, time, switch change situation.
Then Utilities Electric Co. sends Demand Side Response short message to user, voluntarily judges whether to respond by user.The electric appliance if response
Otherwise switch motion terminates process.Utilities Electric Co. can award to the user responded simultaneously.However patent
The maximum defect of CN201510007856.6 is the selection of its heavy dependence user, and frequent progress short message inquiry is not only tight
Ghost image rings the experience of domestic consumer, and automatization level is extremely low, inefficiency.The patent does not account for the control method extremely simultaneously
Dogmatic carry out switching operation largely influences the life comfort level of user.
Summary of the invention:
The technical problem to be solved in the present invention: a kind of home energy source Internet of Things Demand Side Response control neural network based is provided
Method realizes that dynamic manages for the needs of wired home Internet of Things, selects dependence low user, automatization level is high, favorably
User's good experience, can be with overcome the deficiencies in the prior art.
Technical solution of the present invention:
A kind of home energy source Internet of Things Demand Side Response control method neural network based, it includes:
Step 1 carries out real-time data acquisition to household electricity equipment using intelligent electric meter and using collected data as electricity consumption
Sample;
Step 2, neural network algorithm module are trained according to electricity consumption sample, generate habit predicted value, the switch of user power utilization
Probability and weight coefficient simultaneously generate load when household demand side responds according to habit predicted value, switch probability and weight coefficient
Control strategy and Energy Saving Strategy;
Step 3, control module are automatically controlled according to load curtailment strategy and Energy Saving Strategy realizes Demand Side Response movement.
The electricity consumption sample includes electric current, voltage and performance number of the electrical equipment at the discrete series moment, and according to when
Between, season and temperature be grouped in neural network special training.
The switch probability reflects the probability of electrical equipment switch state, and weight coefficient represents the real-time of electrical equipment
Significance level, as needing identical criterion when carrying out Demand Side Response.
Neural network described in step 2 is Bp neural network.
Beneficial effects of the present invention:
1) the degree of automation is higher: the realization that the present invention is responded for electric power demand side at family end provides a kind of automation algorithm
Solution saves a large amount of fringe cost without carrying out cumbersome inquiry, automatic identification and operation to user;
2) algorithm prediction user is higher to the recognition accuracy of the wish of Demand Side Response and the habit of operation: using neural network
To home-use energy digital simulation analysis, the use of prediction user's future time instance can be accustomed to, and the control of inverse living habit can not easily not caused
Work occurs, while will greatly reduce the probability of erroneous judgement user intention using switch probability and weight coefficient as criterion;
3) intelligence degree is high: taking into account Demand Side Response and requires and user's energy.
4) it promotes the adventure in daily life of user: under Automatic Control, in addition to being accustomed to carrying out electrical equipment control according to user, removing use from
The cumbersome operation in family, while some electrical equipments of intelligentized scheduling adjustment such as air-conditioning, make up to comfortably energy saving to people
Working condition.
5) it is often trained by neural network algorithm module according to electricity consumption sample, to constantly be predicted according to habit
Value, switch probability and weight coefficient are adjusted load curtailment strategy and Energy Saving Strategy, realize that dynamic manages, select user
Rely on low, automatization level height, advantageous user's good experience.
Figure of description:
Fig. 1 is specific embodiment of the invention flow diagram.
Specific embodiment:
Embodiment 1. as shown in Figure 1, a kind of home energy source Internet of Things Demand Side Response control method neural network based, it
Including intelligent electric meter, neural network algorithm module, communication module and the control module to household electricity devices collect data, control
Method processed the following steps are included:
Step S1: real-time data acquisition is carried out to household electricity equipment using intelligent electric meter and using collected data as electricity consumption
Sample;The electricity consumption sample includes electric current, voltage, performance number of the electrical equipment at the discrete series moment, and according to time, season
Section and temperature are grouped convenient for neural network special training.
Step S2: neural network algorithm module is trained according to electricity consumption sample, and trained data are known as training set;It generates
Habit predicted value, switch probability and the weight coefficient of user power utilization, do model sample with the trained data, convenient for number later
Load control system when household demand side responds is generated according to comparative analysis, and according to habit predicted value, switch probability and weight coefficient
Strategy and Energy Saving Strategy;The switch probability reflects the probability of electrical equipment switch state, and weight coefficient represents electricity consumption and sets
Standby real-time significance level, as needing identical criterion when carrying out Demand Side Response.The switch probability and weight coefficient
Adjusting is that foundation is obtained using big data sample analysis and according to the statistical method of neural network prediction value, wherein switch
Probability is time-varying, and the coefficient of weight is adjustable;The Energy Saving Strategy be carry out on the basis of load curtailment strategy it is further
What optimization was realized, meanwhile, it also combines adjustment of electricity charges and user is accustomed to the factor of hobby;The neural network is Bp nerve net
Network, while also including the neural network under various algorithm structure systems
Step S3: control module automatically controls according to load curtailment strategy and Energy Saving Strategy and realizes that Demand Side Response acts.
Working principle is as follows, point 3 points of detailed descriptions:
1. sample data learns the stage in advance:
(1) in daily operational process, home energy source Internet of Things carries out real-time data acquisition to household electricity equipment, is put into and adopts
In sample database.
(2) the long-time electricity consumption data sample in database is the training sample set of neural network.Pass through neural network
Training, the day for simulating user, which is commonly used, can be accustomed to (i.e. switch state, the voltage of a certain electrical equipment of some particular moment of one day
The predicted value of current power value, abbreviation predicted value).Predicted value refers to the prediction being accustomed to user, and different weights is presetting
Under have different predicted value samples.
(3) according to more parts of parallel predicted values, parallel predicted value is resulting same i.e. in the same terms, under the identical sampling period
The predicted value of format is compared, and (can set this probability size according to switch probability size as θ), a presetting weight
Coefficient, it is assumed that for α (0 < α < θ, settable α=θ/2 under default situations, α/θ should reduce in sample scarcity), α can also basis
Hobby or laws of use the adjusting gained of user is adjusted and is arranged.
Switching probability is directly obtained by neural network, and what neural network directly obtained is predicted value sample, into
And it is adjusted indirectly according to predicted value sample and obtains switch probability.
(4) with the passage of different time, exist since seasonal variations, user are accustomed to the factors such as variation, it is necessary to adjust again
Whole predicted value, it is therefore desirable to set a time interval, be trained sample set every a time interval and update, and repeat
Tell 1) ~ 3) step, to adapt to change.
2. Demand Side Response task returns the stage:
(1) when the regulation superiors of electric system, which issues Demand Side Response task, to be needed, simulation in advance carries out the judgement control in 3
Stage, and it can be the Demand Side Response task amount realized that it is lower, which to calculate simulation control operation, and return to regulation superiors.
(2) superiors receives home energy source Internet of Things back information, and finally indicates the Demand Side Response task amount assigned.
3. judging the control stage:
(1) judge whether user selects permission system to automatically control Demand Side Response, if it is continue to execute in next step.
(2) power saving class of all electrical equipments is inquired: be divided into and can save energy (can save energy class is to allow to be closed equipment,
Such as lamps and lanterns), not can save energy (not can save energy class is that equipment must open throughout the year, such as refrigerator), (the energy saving class in part is for part energy conservation
Even if can also be reduced by reduction amplitude and be consumed energy, such as air-conditioning, fan for that need not close);For can not economized portion equipment
Directly ignore.Then enter 3) for can save energy with part energy-saving equipment.
(3) the Demand Side Response task amount assigned is indicated according to superiors, acquire real-time electricity consumption data and with the gained of stage 1
Predicted value comparison.If this moment, which switchs probability θ, is greater than weight coefficient α, shows that the equipment is important, is not useable for responding,
If being less than or equal to α, shows that can be used for Demand Side Response is closed or reduces load, and then execute 4), otherwise do not execute.
(4) according to 3) in judgement, data command is sent in family's Internet of Things network control system, execute response action, it is complete
At Demand Side Response task.
Claims (6)
1. a kind of home energy source Internet of Things Demand Side Response control method neural network based, it includes:
Step 1 carries out real-time data acquisition to household electricity equipment using intelligent electric meter and using collected data as electricity consumption
Sample;
Step 2, neural network algorithm module are trained according to electricity consumption sample, generate habit predicted value, the switch of user power utilization
Probability and weight coefficient simultaneously generate load when household demand side responds according to habit predicted value, switch probability and weight coefficient
Control strategy and Energy Saving Strategy;
Step 3, control module are automatically controlled according to load curtailment strategy and Energy Saving Strategy realizes Demand Side Response movement.
2. a kind of home energy source Internet of Things Demand Side Response control method neural network based according to claim 1,
It is characterized by: the electricity consumption sample includes electric current, voltage and performance number of the electrical equipment at the discrete series moment, and according to
Time, season and temperature are grouped in neural network special training.
3. a kind of home energy source Internet of Things Demand Side Response control method neural network based according to claim 1,
It is characterized by: the switch probability reflects the probability of electrical equipment switch state, weight coefficient represents electrical equipment
Real-time significance level, as needing identical criterion when carrying out Demand Side Response.
4. a kind of home energy source Internet of Things Demand Side Response control method neural network based according to claim 1,
It is characterized by: neural network described in step 2 is Bp neural network.
5. home energy source Internet of Things Demand Side Response control strategy neural network based according to claim 1, special
Sign is: switch probability described in step 2 and weight coefficient adjusting are obtained according to big data sample analysis.
6. home energy source Internet of Things Demand Side Response control strategy neural network based according to claim 1, special
Sign is: in step 2, the Energy Saving Strategy is to advanced optimize realization on the basis of load curtailment strategy.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810950629.0A CN109002930A (en) | 2018-08-20 | 2018-08-20 | A kind of home energy source Internet of Things Demand Side Response control method neural network based |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810950629.0A CN109002930A (en) | 2018-08-20 | 2018-08-20 | A kind of home energy source Internet of Things Demand Side Response control method neural network based |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109002930A true CN109002930A (en) | 2018-12-14 |
Family
ID=64592725
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810950629.0A Pending CN109002930A (en) | 2018-08-20 | 2018-08-20 | A kind of home energy source Internet of Things Demand Side Response control method neural network based |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109002930A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109672174A (en) * | 2018-12-20 | 2019-04-23 | 国网北京市电力公司 | Energy management system |
CN110045625A (en) * | 2019-05-13 | 2019-07-23 | 北京科创智汇科技有限责任公司 | A kind of safety control system |
CN110867964A (en) * | 2019-11-26 | 2020-03-06 | 胡维东 | Intelligent electricity utilization safety monitoring method based on Internet of things and main control computer |
CN112288599A (en) * | 2020-10-29 | 2021-01-29 | 四川长虹电器股份有限公司 | Scene service implementation method for smart home, computer device and storage medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102280935A (en) * | 2011-06-24 | 2011-12-14 | 中国科学院电工研究所 | Intelligent power grid management system |
-
2018
- 2018-08-20 CN CN201810950629.0A patent/CN109002930A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102280935A (en) * | 2011-06-24 | 2011-12-14 | 中国科学院电工研究所 | Intelligent power grid management system |
Non-Patent Citations (1)
Title |
---|
赵乾: "基于物联网的建筑智能用电系统的设计与实现", 《中国优秀硕士论文全文数据库工程科技Ⅱ辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109672174A (en) * | 2018-12-20 | 2019-04-23 | 国网北京市电力公司 | Energy management system |
CN110045625A (en) * | 2019-05-13 | 2019-07-23 | 北京科创智汇科技有限责任公司 | A kind of safety control system |
CN110867964A (en) * | 2019-11-26 | 2020-03-06 | 胡维东 | Intelligent electricity utilization safety monitoring method based on Internet of things and main control computer |
CN112288599A (en) * | 2020-10-29 | 2021-01-29 | 四川长虹电器股份有限公司 | Scene service implementation method for smart home, computer device and storage medium |
CN112288599B (en) * | 2020-10-29 | 2022-03-01 | 四川长虹电器股份有限公司 | Scene service implementation method for smart home, computer device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109002930A (en) | A kind of home energy source Internet of Things Demand Side Response control method neural network based | |
CN109340904B (en) | Electric heating collaborative optimization operation method | |
CN106096778A (en) | A kind of household electricity planning system based on tou power price and step price form and method | |
CN109687465B (en) | Active power distribution network load elastic control system | |
CN101968651B (en) | Wireless mode based building energy-conservation monitoring system | |
CN107248017B (en) | Real-time power generation plan optimization method considering cogeneration | |
CN103293961B (en) | Energy efficiency power plant modeling and integrating method based on demand response control | |
CN111478349A (en) | Power three-phase balance strategy method based on power utilization equipment intelligent network regulation and control Internet of things | |
CN106707807B (en) | Water dispenser and its intelligent control method based on sequential, system | |
CN112307675B (en) | Neural network-based temperature-sensitive load separation identification method and system | |
CN102103362A (en) | Micro-grid system and micro-grid system-based fuzzy control method | |
CN206370695U (en) | A kind of photovoltaic plant | |
CN108364120A (en) | Intelligent residential district demand response cutting load method based on user power utilization irrelevance | |
CN204144950U (en) | A kind of compensation program control circuit on-load voltage regulation system | |
Fan et al. | Study on load monitoring and demand side management strategy based on Elman neural network optimized by sparrow search algorithm | |
CN203324736U (en) | Climate-compensation controller | |
CN206193481U (en) | Gas heating boiler's intelligence control system | |
CN108335043A (en) | A kind of intelligent electricity utilization cell cutting load dispatching method of fairness | |
CN114648209A (en) | Building energy equipment energy-saving management system based on Internet of things cloud platform | |
CN107392480A (en) | A kind of meter and family's workload demand of electricity consumption behavior respond in a few days dispatching method | |
CN210264931U (en) | Biogas generator set control system based on intelligent cloud | |
CN208188658U (en) | Internet+intelligent heat-exchange station control device | |
CN105022376A (en) | Domestic energy efficiency management method based on time-of-use electricity price | |
Abdelwahed et al. | Internet of things based energy management system using real-time consumption data | |
CN111769548A (en) | Remote intelligent regulation and control system and method for distribution transformer |
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: 20181214 |