CN107300857B - Electric energy management system for sensing indoor environment information - Google Patents
Electric energy management system for sensing indoor environment information Download PDFInfo
- Publication number
- CN107300857B CN107300857B CN201710577925.6A CN201710577925A CN107300857B CN 107300857 B CN107300857 B CN 107300857B CN 201710577925 A CN201710577925 A CN 201710577925A CN 107300857 B CN107300857 B CN 107300857B
- Authority
- CN
- China
- Prior art keywords
- data
- energy consumption
- indoor environment
- sample
- input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an electric energy management system for sensing indoor environment information, which comprises: the system comprises an acquisition module, a transmission module, an upper computer and a background server. The acquisition module uploads the acquired data to the upper computer through the transmission module. And then, the upper computer displays the data and transmits the data to the background server. And the background server evaluates and analyzes the collected indoor environment data and the collected electric appliance energy consumption data. And finally, transmitting the data analysis result to the controller unit so as to adjust the working state of the electric appliance. Due to the addition of the acquisition module, the accurate measurement of temperature, humidity, ambient light intensity, PM2.5 and smoke information is realized. The background server is used for storing the collected indoor environment data and the collected electric appliance energy consumption data, establishing an environment energy consumption database, evaluating the current power utilization state, calculating an optimal scheme and adjusting the power consumption more accurately and actively.
Description
Technical Field
The invention belongs to the field of intelligent electric energy management, and particularly relates to an electric energy management system for sensing indoor environment information.
Background
The energy consumption of indoor electrical equipment is always a concern and a problem to be solved, the use of the indoor electrical equipment is closely related to the indoor environment conditions, for example, the indoor temperature and humidity can affect the electric energy generated by the air conditioner, and other indoor environmental factors can also affect the electric energy of the electrical equipment, such as the regulation of the lighting equipment on the ambient light.
At present, a lot of intelligent schemes aiming at electric energy management of electric equipment are provided, energy-saving efficiency is improved by adopting new energy-saving equipment in a common mode, and intelligent home management schemes are adopted by some intelligent communities. In terms of energy management, domestic experts and scholars propose an intelligent energy management method based on a neural network, for example, the chinese patent publication No. CN105045096A, but the method only trains energy consumption data of hardware devices to obtain an optimal solution and sets a load threshold value to realize intelligent management of energy consumption, but does not consider surrounding environmental factors, thereby having certain limitations.
Therefore, it is necessary to provide a method and an apparatus for indoor power management by sensing environmental information, which integrate a neural network algorithm, refine depth features of monitoring data, and implement adaptive management of indoor power.
Disclosure of Invention
The invention provides an electric energy management system for sensing indoor environment information, which takes the sensed indoor environment information and electric appliance load data as a real-time data set, trains the data set through a wavelet neural network algorithm, learns indoor user habits and obtains a self-adaptive indoor electric energy management prediction model.
The specific technical scheme of the invention is as follows:
an electric energy management system for sensing indoor environment information comprises an electric appliance, an acquisition module, a transmission module, an upper computer, a background server and a controller unit. The acquisition module acquires indoor environment data and electric appliance energy consumption data of the electric appliances and uploads the data to the upper computer through the transmission module. And the upper computer displays the data and transmits the data to the background server. The background server evaluates and analyzes the collected indoor environment data and the collected electric appliance energy consumption data, and transmits the data analysis result to the controller unit, so as to adjust the working state of the electric appliance.
The acquisition module comprises a sensor node unit and an electrical appliance energy consumption metering unit and is used for acquiring indoor environment data and electrical appliance energy consumption data.
The transmission module collects the data collected by the collection module and then sends the data to the upper computer. The working modes of the transmission module comprise wired transmission and wireless transmission.
The upper computer is provided with a display terminal for displaying the data acquired by the acquisition module in real time.
The background server firstly stores the collected indoor environment data and the collected electric appliance energy consumption data and establishes an environment energy consumption database; training data in the environmental energy consumption database to obtain data characteristics of environment and energy consumption, and updating the environmental energy consumption database; meanwhile, comparing the current indoor environment and the energy consumption conditions of the electric appliances with the data in the environment energy consumption database to obtain an indoor environment evaluation result, and adjusting the current indoor environment data and the energy consumption data of the electric appliances to enable the current indoor environment data and the energy consumption data of the electric appliances to be close to an expected output value, thereby obtaining an electric energy optimization scheme.
And the controller unit receives the electric energy optimization scheme and adjusts the working state of the indoor electric appliance according to the optimization scheme.
Further, the sensor node unit of the acquisition module comprises a temperature and humidity sensing node, an indoor environment light sensing node, a PM2.5 sensing node and a smoke sensing node.
Further, the training of the data in the database is completed through a wavelet neural network algorithm. The wavelet neural network algorithm is to combine the neural network and wavelet transformation to establish a data processing model and extract data characteristics.
Further, the wavelet neural network algorithm specifically comprises the following processes:
step one, taking environment data and electrical appliance energy consumption data as input samples of a wavelet neural network model; each input sample serves as a training set: s ═ xk,yj}; wherein xkAs environmental data, yjFor the power consumption data of the electrical appliances, k is differentThe environment variable j is different electrical appliances.
Step two, decomposing and processing the input sample, finding out an ideal input sample and putting the ideal input sample into a database, specifically comprising the following steps: taking the input samples as a group of discrete time signal sequences S (i), calculating a mean value sequence of the input samples
N is the number of input samples; defining a target error rate for the input samples:
if the target error rate of the input sample is less than 1, the input sample is an ideal input sample; otherwise, the sample is an undesirable sample; while providing a prediction of the data samples at the next time instant at the output layer.
Segmenting the undesirable sample, and adjusting the weight of each layer of the wavelet neural network to enable the adjusted undesirable sample to be close to an ideal output value; the method specifically comprises the following steps: taking an undesirable sample as the input of a wavelet algorithm, and performing scale decomposition through wavelet transformation; reconstructing the decomposed undesirable sample, reducing the undesirable sample to the original scale, and using the undesirable sample as the input quantity of the neural network model; then, collecting data samples of 3 weeks, taking the data samples of the first week as input, taking the data samples of the second week as output, carrying out modeling training by using a frame of a wavelet neural network to obtain network weight values of each connection layer, and then taking the data samples collected of the second week as input to obtain prediction output of the third week; comparing the predicted output with the true value to find out error factors; if the error is larger, the training is carried out again until the true value is approached.
Step four, forming a new time sequence Z (i) by the ideal input sample and the non-ideal sample after wavelet transformation reconstruction, and extracting the variance of Z (i) as
(ii) as a data feature of Z (i), wherein q (i) is a mean sequence of Z (i),
σ2the evaluation index is used for reflecting the fluctuation range of each section of input sample data and is used as the evaluation index for comparing the input sample data.
Further, the upper computer is terminal display software and is used for displaying indoor environment data and electric appliance energy consumption data and uploading the data to the background server in an FTP mode.
Further, the transmission module comprises a carrier transceiver module and a serial port communication module. And the carrier transceiver module transmits the data of the acquisition module to the serial port communication module through a carrier medium. And then the serial port communication module sends the data to an upper computer.
Furthermore, the electric appliance energy consumption metering unit realizes the statistics and calculation of the electric quantity of the electric appliance through the microcontroller and the voltage current transformer.
Further, the decomposition scale of the wavelet transform in the fourth step is 3, and the wavelet function adopts a db5 wavelet.
The invention has the following beneficial effects:
1. the collection module is added, so that accurate measurement of temperature and humidity, ambient light intensity, PM2.5 and smoke information is achieved, and the electricity consumption of the electric equipment is collected in real time.
2. The background server stores the collected indoor environment data and the collected electric appliance energy consumption data, establishes an environment energy consumption database, evaluates the current power utilization state, calculates an optimal scheme, and realizes the adjustment of the power consumption more accurately and actively.
3. The data in the database are trained by adopting a wavelet neural network algorithm to finish training and machine learning, the database is established, a preferred scheme is provided according to the energy consumption condition, the power consumption state of the electric appliance is adjusted according to the power consumption habits of users and indoor environment data, the method is more scientific and energy-saving, and the intellectualization of electric energy management is realized.
Drawings
FIG. 1 is a system framework diagram of the present invention;
FIG. 2 is a system workflow diagram of an example of the invention.
Detailed Description
The invention is described with reference to the accompanying drawings.
As shown in fig. 1, an electric energy management system for sensing indoor environment information includes an electric appliance 13, an acquisition module 1, a transmission module 7, an upper computer 8, a background server 9, and a controller unit 12.
Wherein, collection module 1 includes: and the sensor node unit and the electric appliance energy consumption metering unit 6 are mainly responsible for collecting indoor environment data and electric appliance energy consumption data. The sensor node unit specifically includes: temperature and humidity perception node 2, indoor environment light perception node 3, PM2.5 perception node 4, smog perception node 5 etc.. The electric appliance energy consumption metering unit 6 realizes the statistics and calculation of the electric quantity of the electric appliance through the microcontroller and the voltage current transformer.
The transmission module 7 comprises a carrier transceiver module 10 and a serial port communication module 11; the carrier transceiver module 10 transmits the data transmitted by the acquisition module 1 to the serial port communication module 11 through a carrier medium.
The upper computer 8 is provided with a display terminal for displaying the data acquired by the acquisition module in real time. The display terminal of the upper computer is developed through Delphi7.0, the upper computer can complete serial port communication with the lower computer by calling the MSComm control, and calls the FTP control to realize uploading of data to a background server;
as shown in fig. 2, the working process of the power management system is as follows: the acquisition module 1 acquires indoor environment data and electric appliance energy consumption data of the electric appliances 13 and uploads the data to the upper computer 8 through the transmission module 7. The upper computer 8 displays the data and transmits the data to the background server 9. The background server 9 evaluates and analyzes the collected indoor environment data and the collected electric appliance energy consumption data, and adjusts the current indoor environment data and the current electric appliance energy consumption data to be close to the expected output value, so as to obtain an electric energy optimization scheme, thereby achieving the purpose of reducing the electric appliance energy consumption.
Specifically, the background server 9 first stores the collected indoor environment data and the collected electric appliance energy consumption data and establishes an environment energy consumption database; training data in the environmental energy consumption database to obtain data characteristics of environment and energy consumption, and updating the environmental energy consumption database; meanwhile, comparing the current indoor environment and the energy consumption conditions of the electric appliances with the data in the environment energy consumption database to obtain an indoor environment evaluation result, and adjusting the current indoor environment data and the energy consumption data of the electric appliances to enable the current indoor environment data and the energy consumption data of the electric appliances to be close to an expected output value, thereby obtaining an electric energy optimization scheme.
The development environment of the background server is Eclipse, a Tomcat server and a MySQ L database, and the expected output value can be set by a user or obtained by training according to the habit of the user.
The training of the data in the database is completed by a wavelet neural network algorithm. The wavelet neural network algorithm is to combine the neural network and wavelet transformation to establish a data processing model and extract data characteristics. The specific process is as follows:
step one, taking environment data and electrical appliance energy consumption data as input samples of a wavelet neural network model; each input sample serves as a training set: s ═ xk,yj}; wherein xkAs environmental data, yjThe energy consumption data of the electrical appliances are shown, k is different environment variables, and j is different electrical appliances.
Step two, decomposing and processing the input sample, finding out an ideal input sample and putting the ideal input sample into a database, specifically comprising the following steps: taking the input samples as a group of discrete time signal sequences S (i), calculating a mean value sequence of the input samples
N is the number of input samples; defining a target error rate for the input samples:
1, 2.; if the target error rate of the input sample is less than 1, the input sample is an ideal input sample; otherwise, the sample is an undesirable sample; while providing a prediction of the data samples at the next time instant at the output layer.
Segmenting the undesirable sample, and adjusting the weight of each layer of the wavelet neural network to enable the adjusted undesirable sample to be close to an ideal output value; the method specifically comprises the following steps: taking an undesirable sample as the input of a wavelet algorithm, and performing scale decomposition through wavelet transformation; reconstructing the decomposed undesirable sample, reducing the undesirable sample to the original scale, and using the undesirable sample as the input quantity of the neural network model; then, collecting data samples of 3 weeks, taking the data samples of the first week as input, taking the data samples of the second week as output, carrying out modeling training by using a frame of a wavelet neural network to obtain network weight values of each connection layer, and then taking the data samples collected of the second week as input to obtain prediction output of the third week; comparing the predicted output with the true value to find out error factors; if the error is larger, the training is carried out again until the true value is approached.
Step four, forming a new time sequence Z (i) by the ideal input sample and the non-ideal sample after wavelet transformation reconstruction, and extracting the variance of Z (i) as
(ii) as a data feature of Z (i), wherein q (i) is a mean sequence of Z (i),
σ2the evaluation index is used for reflecting the fluctuation range of each section of input sample data and is used as the evaluation index for comparing the input sample data.
Claims (6)
1. The utility model provides an electric energy management system of perception indoor environmental information which characterized in that: the system comprises an electric appliance (13), an acquisition module (1), a transmission module (7), an upper computer (8), a background server (9) and a controller unit (12); the acquisition module (1) acquires indoor environment data and electric appliance energy consumption data of an electric appliance (13), and uploads the data to the upper computer (8) through the transmission module (7); the upper computer (8) displays the data and transmits the data to the background server (9); the background server (9) evaluates and analyzes the collected indoor environment data and the collected electric appliance energy consumption data, and transmits the data analysis result to the controller unit (12), so as to adjust the working state of the electric appliance (13);
the acquisition module (1) comprises a sensor node unit and an electrical appliance energy consumption metering unit (6) and is used for acquiring indoor environment data and electrical appliance energy consumption data;
the transmission module collects the data collected by the collection module and then sends the data to the upper computer (8); the working modes of the transmission module comprise wired transmission and wireless transmission;
the upper computer (8) is provided with a display terminal for displaying the data acquired by the acquisition module in real time;
the background server (9) firstly stores the collected indoor environment data and the collected electric appliance energy consumption data and establishes an environment energy consumption database; training data in the environmental energy consumption database to obtain data characteristics of environment and energy consumption, and updating the environmental energy consumption database; meanwhile, comparing the current indoor environment and the energy consumption conditions of the electric appliances with the data in the environment energy consumption database to obtain an indoor environment evaluation result, and adjusting the current indoor environment data and the energy consumption data of the electric appliances to be close to an expected output value so as to obtain an electric energy optimization scheme;
the controller unit receives the electric energy optimization scheme and adjusts the working state of the indoor electric appliance (13) according to the optimization scheme;
the training of the data in the database is completed through a wavelet neural network algorithm; the wavelet neural network algorithm is to establish a data processing model and extract data characteristics by combining a neural network and wavelet transformation;
the wavelet neural network algorithm comprises the following specific processes:
step one, taking environment data and electrical appliance energy consumption data as input samples of a wavelet neural network model; each input sample serves as a training set: s ═ xk，yj}; wherein xkAs environmental data, yjThe energy consumption data of the electrical appliances are shown, k is different environment variables, and j is different electrical appliances;
step two, decomposing and processing the input sample, finding out an ideal input sample and putting the ideal input sample into a database, specifically comprising the following steps: taking the input samples as a group of discrete time signal sequences S (i), calculating a mean value sequence of the input samples
N is the number of input samples; defining a target error rate for the input samples:
if the target error rate of the input sample is less than 1, the input sample is an ideal input sample; otherwise, the sample is an undesirable sample; simultaneously providing data sample prediction at the next time instant at the output layer;
segmenting the undesirable sample, and adjusting the weight of each layer of the wavelet neural network to enable the adjusted undesirable sample to be close to an ideal output value; the method specifically comprises the following steps: taking an undesirable sample as the input of a wavelet algorithm, and performing scale decomposition through wavelet transformation; reconstructing the decomposed undesirable sample, reducing the undesirable sample to the original scale, and using the undesirable sample as the input quantity of the neural network model; then, collecting data samples of 3 weeks, taking the data samples of the first week as input, taking the data samples of the second week as output, carrying out modeling training by using a frame of a wavelet neural network to obtain network weight values of each connection layer, and then taking the data samples collected of the second week as input to obtain prediction output of the third week; comparing the predicted output with the true value to find out error factors; if the error is larger, the training is carried out again until the true value is approached;
step four, forming a new time sequence Z (i) by the ideal input sample and the non-ideal sample after wavelet transformation reconstruction, and extracting the variance of Z (i) as
(ii) as a data feature of Z (i), wherein q (i) is a mean sequence of Z (i),
σ2the evaluation index is used for reflecting the fluctuation range of each section of input sample data and is used as the evaluation index for comparing the input sample data.
2. The power management system for sensing indoor environment information of claim 1, wherein: the sensor node unit of the acquisition module (1) comprises a temperature and humidity sensing node (2), an indoor environment light sensing node (3), a PM2.5 sensing node (4) and a smoke sensing node (5).
3. The power management system for sensing indoor environment information of claim 1, wherein: the upper computer is terminal display software and is used for displaying indoor environment data and electric appliance energy consumption data and uploading the data to the background server (9) in an FTP mode.
4. A power management system for sensing indoor environment information according to any one of claims 1 to 3, wherein: the transmission module (7) comprises a carrier transceiver module (10) and a serial port communication module (11); the carrier transceiver module (10) transmits the data of the acquisition module (1) to the serial port communication module (11) through a carrier medium; and then the serial port communication module (11) sends the data to the upper computer (8).
5. A power management system for sensing indoor environment information according to any one of claims 1 to 3, wherein: the electric appliance energy consumption metering unit (6) realizes the statistics and calculation of electric quantity of the electric appliance through the microcontroller and the voltage current transformer.
6. A power management system for sensing indoor environment information according to any one of claims 1 to 3, wherein: the decomposition scale of the wavelet transform in the fourth step is 3, and the wavelet function adopts a db5 wavelet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710577925.6A CN107300857B (en) | 2017-07-15 | 2017-07-15 | Electric energy management system for sensing indoor environment information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710577925.6A CN107300857B (en) | 2017-07-15 | 2017-07-15 | Electric energy management system for sensing indoor environment information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107300857A CN107300857A (en) | 2017-10-27 |
| CN107300857B true CN107300857B (en) | 2020-07-24 |
Family
ID=60132850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710577925.6A Active CN107300857B (en) | 2017-07-15 | 2017-07-15 | Electric energy management system for sensing indoor environment information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107300857B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682349A (en) * | 2012-05-14 | 2012-09-19 | 云南电力试验研究院（集团）有限公司电力研究院 | Electricity consumption intelligent prediction system and method |
| CN104598986A (en) * | 2014-12-12 | 2015-05-06 | 国家电网公司 | Big data based power load prediction method |
| EP2944786A1 (en) * | 2014-05-17 | 2015-11-18 | MAN Truck & Bus AG | Control or regulation method for a motor vehicle |
| CN106327028A (en) * | 2016-11-09 | 2017-01-11 | 国网能源研究院 | Terminal energy consumption prediction method and device |
| CN106707999A (en) * | 2017-02-09 | 2017-05-24 | 苏州科技大学 | Building energy-saving system based on self-adaptive controller, control method and simulation |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0808012A1 (en) * | 1992-07-03 | 1997-11-19 | EURO CP s.a.r.l. | Method for managing the tariff of electrical power in a network of a room |
| CN101236430A (en) * | 2008-02-26 | 2008-08-06 | 浙江省建筑科学设计研究院有限公司 | Wireless inner network architecture energy consumption and environment real time monitoring and analytical method |
| KR101364508B1 (en) * | 2012-11-23 | 2014-02-19 | (주) 티아이에스 | Intergrated monitoring system for indoor enviroment |
| CN103136598B (en) * | 2013-02-26 | 2016-08-24 | 福建省电力有限公司 | Monthly calculation of power load machine Forecasting Methodology based on wavelet analysis |
| CN105320184B (en) * | 2014-11-26 | 2017-11-14 | 华北电力大学 | Building Indoor Environment intelligent monitor system |
| CN105825323A (en) * | 2016-03-10 | 2016-08-03 | 山东建筑大学 | Building energy consumption main influence factor analysis method based on big data |
| CN106444541A (en) * | 2016-11-23 | 2017-02-22 | 天津生态城绿色建筑研究院有限公司 | Intellectualized monitoring and operation optimization method and system of green building |
-
2017
- 2017-07-15 CN CN201710577925.6A patent/CN107300857B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682349A (en) * | 2012-05-14 | 2012-09-19 | 云南电力试验研究院（集团）有限公司电力研究院 | Electricity consumption intelligent prediction system and method |
| EP2944786A1 (en) * | 2014-05-17 | 2015-11-18 | MAN Truck & Bus AG | Control or regulation method for a motor vehicle |
| CN104598986A (en) * | 2014-12-12 | 2015-05-06 | 国家电网公司 | Big data based power load prediction method |
| CN106327028A (en) * | 2016-11-09 | 2017-01-11 | 国网能源研究院 | Terminal energy consumption prediction method and device |
| CN106707999A (en) * | 2017-02-09 | 2017-05-24 | 苏州科技大学 | Building energy-saving system based on self-adaptive controller, control method and simulation |
Non-Patent Citations (3)
| Title |
|---|
| 《Fuzzy Wavelet Neural Networks for City Electric Energy Consumption Forecasting》;Ping Zhang 等;《Energy Procedia》;20121231;第1332-1338页 * |
| 《基于小波神经网络模型的中国能耗预测》;周仲礼 等;《成都理工大学学报(自然科学版)》;20051031;第543-547页 * |
| 《电力扰动数据分析学——电能质量监测数据的新应用》;徐文远 等;《中国电机工程学报》;20130705;第93-101页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107300857A (en) | 2017-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108488987B (en) | Control method of air conditioning apparatus, storage medium, and apparatus | |
| CN105045234B (en) | Wired home energy management method based on intelligence wearable device behavior perception | |
| CN108413588B (en) | Personalized air conditioner control system and method based on thermal imaging and BP neural network | |
| CN108446021B (en) | Application method of P300 brain-computer interface in intelligent home based on compressed sensing | |
| CN109489212B (en) | Intelligent sleep control method, adjustment system and equipment for air conditioner | |
| CN104122819A (en) | User habit based intelligent household electricity utilization method and system thereof | |
| CN107392391A (en) | A kind of electric load electricity consumption decomposition method based on deep learning | |
| CN108054749B (en) | Non-invasive power load decomposition method and device | |
| CN106067079A (en) | A kind of system and method for gray haze based on BP neutral net prediction | |
| CN105320184A (en) | Intelligent monitoring system of indoor environment of building | |
| CN111242276B (en) | One-dimensional convolutional neural network construction method for load current signal identification | |
| CN108613332A (en) | A kind of energy-saving building film micro area personnel interactive mode hot comfort adjusting method | |
| CN109471370A (en) | A kind of behavior prediction and control method based on exhaust fan operation data, system | |
| CN110471301A (en) | A kind of smart home service recommendation system and method based on user behavior | |
| CN113359486A (en) | Intelligent window system based on neural network algorithm regulation and control and regulation method | |
| CN113923839A (en) | Light adjusting method and system | |
| CN114690660A (en) | Electric appliance control system based on smart home | |
| CN109270848A (en) | Recommended method, server, household appliance and the storage medium of contextual model | |
| CN114997508A (en) | Greenhouse electricity utilization optimization method and system based on multi-energy complementation | |
| CN117762032B (en) | Intelligent equipment control system and method based on scene adaptation and artificial intelligence | |
| CN117628678A (en) | Energy-saving air conditioner control panel based on wireless network control | |
| CN108426349B (en) | Air conditioner personalized health management method based on complex network and image recognition | |
| CN107300857B (en) | Electric energy management system for sensing indoor environment information | |
| CN112378052A (en) | Indoor comfort degree adjusting method, device and system, computer equipment and storage medium | |
| CN105182811A (en) | User intelligent service method and system based on operation of electrical equipment |
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 |