CN105045096A - Intelligent energy saving method based on neural network and system thereof - Google Patents
Intelligent energy saving method based on neural network and system thereof Download PDFInfo
- Publication number
- CN105045096A CN105045096A CN201510526523.4A CN201510526523A CN105045096A CN 105045096 A CN105045096 A CN 105045096A CN 201510526523 A CN201510526523 A CN 201510526523A CN 105045096 A CN105045096 A CN 105045096A
- Authority
- CN
- China
- Prior art keywords
- energy
- energy consumption
- consumption data
- bottom hardware
- neural network
- 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
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention relates to the intelligent energy saving field and discloses an intelligent energy saving method based on a neural network and a system thereof. Energy consumption data of bottom hardware is acquired and the energy consumption data is sent to an intelligent energy management platform. The intelligent energy management platform acquires an approximate optimal solution of the energy consumption data by using a trained BP neural network according to the energy consumption data of the bottom hardware and determines an energy saving optimization strategy according to the approximate optimal solution and a preset load threshold. According to the energy saving optimization strategy, a control parameter of the bottom hardware is adjusted so as to optimize the energy consumption of the bottom hardware. By using the method and the system, energy scheduling of the energy management platform and far-end energy saving control optimization are realized.
Description
Technical field
The present invention relates to wisdom energy field, particularly relate to a kind of wisdom energy power-economizing method based on neural network and system.
Background technology
Along with infotech high speed; within 2014, rise; " energy internet " word sweeps across energy circle; Internet of Things, the large technology such as data, intellectuality are applied to traditional energy industry gradually; utilize four of internet " Opening, real time implementation, datumization, scale " large advantages; apply the Internet technologies such as large data, cloud computing and build energy-saving monitoring and wisdom energy management platform; realize intelligent dynamic adaptation energy production, transmission and consumption; reach raise the efficiency, the effect such as energy-saving and emission-reduction, become trend of the times.
At present, energy-saving monitoring and energy management platform adopt three-tier architecture usually, and the bottom is measuring instrument, sensor or actuating unit; Second sublevel is all kinds of gateway, achieves concentrated collection, protocol conversion, data transmission the function such as to assign with steering order; Third layer is data center, realizes Various types of data centralized management, based on cloud computing, large data, provides the functions such as data statistic analysis, diagnosis of energy saving and Energy Saving Control optimization.
The technology such as the Data acquisition and transmit control of bottom are comparatively ripe, substantially standardization, industrialization has been achieved, and all kinds of gateway device is in the core position formed a connecting link in whole system framework, traditional gateway device wisdom limitation, mostly can only complete underlying protocol conversion, Data acquisition and transmit effect, there is the problems such as connectivity difference, operational performance are poor, function singleness, energy management platform cannot carry out energy scheduling and the optimization of far-end Energy Saving Control.
Summary of the invention
The invention provides a kind of wisdom energy power-economizing method based on neural network and system, solve energy management platform in prior art and cannot carry out the technical matters that energy scheduling and far-end Energy Saving Control optimize.
The object of the invention is to be achieved through the following technical solutions:
Based on a wisdom energy power-economizing method for neural network, comprising:
Obtain the energy consumption data of bottom hardware, and described energy consumption data is sent to wisdom energy management platform;
Described wisdom energy management platform, according to the described energy consumption data of bottom hardware, utilizes trained BP neural network to obtain the approximate optimal solution of energy consumption data, according to described approximate optimal solution and the load threshold pre-set, determines energy saving optimizing strategy;
According to described energy saving optimizing strategy, regulate the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.
Based on a wisdom energy energy conserving system for neural network, it is characterized in that, comprising:
Access gateway, for obtaining the energy consumption data of bottom hardware, and is sent to wisdom energy management platform by described energy consumption data;
Wisdom energy management platform, for receiving the described energy consumption data of bottom hardware, utilizes trained BP neural network to obtain the approximate optimal solution of energy consumption data, according to described approximate optimal solution and the load threshold pre-set, determines energy saving optimizing strategy; Described energy saving optimizing strategy is sent to described access gateway;
Access gateway, also for receiving described energy saving optimizing strategy, according to described energy saving optimizing strategy, regulates the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.
The invention provides a kind of wisdom energy power-economizing method based on neural network and system, by obtaining the energy consumption data of bottom hardware, and described energy consumption data being sent to wisdom energy management platform; Described wisdom energy management platform, according to the described energy consumption data of bottom hardware, utilizes trained BP neural network to obtain the approximate optimal solution of energy consumption data, according to described approximate optimal solution and the load threshold pre-set, determines energy saving optimizing strategy; According to described energy saving optimizing strategy, regulate the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.Present invention achieves energy scheduling and the optimization of far-end Energy Saving Control of energy management platform.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, also can obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the application scenarios figure of the embodiment of the present invention;
A kind of wisdom energy power-economizing method process flow diagram based on neural network that Fig. 2 provides for the embodiment of the present invention;
The structural representation of a kind of wisdom energy energy conserving system based on neural network that Fig. 3 provides for the embodiment of the present invention.
Embodiment
For enabling above-mentioned purpose of the present invention, feature and advantage become apparent more, and below in conjunction with the drawings and specific embodiments, the present invention is further detailed explanation.
Be illustrated in figure 1 the application scenarios figure of the embodiment of the present invention, the application of whole scene is based on IEEE1888 standard, IEEE1888 by telecommunication network, realizes carrying out unified management, Based Intelligent Control to the power consumption facility in community on a large scale, reaches energy consumption monitoring, object that energy consumption is saved.Figure medium-long range wisdom energy management platform, by IEEE1888 access gateway, is connected with sensor, measuring instrument, actuating unit, and long-range wisdom energy management platform is monitored by the energy consumption of IEEE1888 access gateway to network.Below in conjunction with Fig. 1, introduce a kind of wisdom energy power-economizing method based on neural network in detail, as shown in Figure 2, comprising:
The energy consumption data of step 201, acquisition bottom hardware, and described energy consumption data is sent to wisdom energy management platform;
Wherein, bottom hardware comprises sensor, actuating unit, measuring instrument.
Step 201 specifically can comprise:
The energy consumption data of step 201-1, collection bottom hardware;
Step 201-2, described energy consumption data to be compressed;
Step 201-3, by the energy consumption data after described compression, by IEEE1888 data channel encryption be sent to wisdom energy management platform.
Step 202, described wisdom energy management platform are according to the described energy consumption data of bottom hardware, trained BP neural network is utilized to obtain the approximate optimal solution of energy consumption data, according to described approximate optimal solution and the load threshold pre-set, determine energy saving optimizing strategy;
Wherein, in step 202, a load threshold is at least set.If load is higher than load threshold, then need to fall load operation to data center; If load is lower than load threshold, then do not need to carry out energy saving optimizing operation to data center.
Before step 202, comprising:
Using the described energy consumption data of the bottom hardware of acquisition as the input of LM algorithm, BP neural network is trained.
In this step, data center adopts BP neural network to realize.BP neural network is a kind of Multi-layered Feedforward Networks by Back Propagation Algorithm training, can learn and store a large amount of input-output mode map relations, and without the need to disclosing the math equation describing this mapping relations in advance.The learning rules of BP neural network use method of steepest descent, constantly adjusted the weights and threshold of network, make the error sum of squares of network minimum by backpropagation.LM algorithm is a kind of fast algorithm utilizing the numerical optimization technique of standard, is the combination of gradient descent method and Gauss-Newton method, is the local convergence of the improved form of Gauss-Newton method, its existing Gauss-Newton method, has again the global property of gradient descent method.LM algorithm utilizes approximate second derivative information, and its speed of convergence is better than gradient descent method.
Concrete, in this step, data center, based on the load data of the large-scale data center obtained in advance, adopts LM (Levenberg-Marquardt) algorithm to train BP neural network.Each energy consumption data is four-dimensional input vector P:
P={x1,x2,x3,x4},
Wherein, x1 represents sensor energy consumption, and x2 represents measuring instrument energy consumption, x3 actuating unit energy consumption, and x4 is the factor of other influences building energy consumption, such as outdoor climate conditions, personnel activity's rule, office equipment Changing Pattern, equipment moving law etc.
In other implementations, energy consumption data can be set as other dimension input vectors, does not limit at this.
LM algorithm is from higher load data as initial input, and current load data is repeated to the iteration of " produce new explanation → calculating target function poor → accept or give up ", join probability kick characteristic finds load approximate optimal solution in solution space.BP neural network through constantly training can improve the speed of convergence obtaining optimum solution.
Specifically how to utilize LM algorithm BP neural network to be trained to the conventional techniques means belonging to those skilled in the art, the protection domain that its specific implementation is not intended to limit the present invention, repeat no more here.
Step 203, according to described energy saving optimizing strategy, regulate the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.
Wherein, described access gateway 310 receives described energy saving optimizing strategy, according to described energy saving optimizing strategy, regulates the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.
The invention provides a kind of wisdom energy power-economizing method based on neural network and system, by obtaining the energy consumption data of bottom hardware, and described energy consumption data being sent to wisdom energy management platform; Described wisdom energy management platform, according to the described energy consumption data of bottom hardware, utilizes trained BP neural network to obtain the approximate optimal solution of energy consumption data, according to described approximate optimal solution and the load threshold pre-set, determines energy saving optimizing strategy; According to described energy saving optimizing strategy, regulate the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.Present invention achieves energy scheduling and the optimization of far-end Energy Saving Control of energy management platform.
The embodiment of the present invention additionally provides a kind of wisdom energy energy conserving system based on neural network, as shown in Figure 3, comprising:
Access gateway 310, for obtaining the energy consumption data of bottom hardware, and is sent to wisdom energy management platform by described energy consumption data;
Wisdom energy management platform 320, for receiving the described energy consumption data of bottom hardware, utilizes trained BP neural network to obtain the approximate optimal solution of energy consumption data, according to described approximate optimal solution and the load threshold pre-set, determines energy saving optimizing strategy; Described energy saving optimizing strategy is sent to described access gateway;
Described access gateway 310, also for receiving described energy saving optimizing strategy, according to described energy saving optimizing strategy, regulates the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.
Wherein, native system also comprises bottom hardware 330, and described bottom hardware 330 comprises sensor, actuating unit, measuring instrument.
Above to invention has been detailed introduction, applying specific case herein and setting forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping; Meanwhile, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (6)
1., based on a wisdom energy power-economizing method for neural network, it is characterized in that, comprising:
Obtain the energy consumption data of bottom hardware, and described energy consumption data is sent to wisdom energy management platform;
Described wisdom energy management platform, according to the described energy consumption data of bottom hardware, utilizes trained BP neural network to obtain the approximate optimal solution of energy consumption data, according to described approximate optimal solution and the load threshold pre-set, determines energy saving optimizing strategy;
According to described energy saving optimizing strategy, regulate the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.
2. the wisdom energy power-economizing method based on neural network according to claim 1, it is characterized in that, bottom hardware comprises sensor, actuating unit, measuring instrument.
3. the wisdom energy power-economizing method based on neural network according to claim 1, is characterized in that, described described energy consumption data is sent to wisdom energy management platform, comprising:
Described energy consumption data is compressed;
By the energy consumption data after described compression, be sent to wisdom energy management platform by the encryption of IEEE1888 data channel.
4. the wisdom energy power-economizing method based on neural network according to claim 1, is characterized in that, according to the described energy consumption data of bottom hardware, utilizes before trained BP neural network obtains the step of the approximate optimal solution of energy consumption data, comprising:
Using the described energy consumption data of the bottom hardware of acquisition as the input of LM algorithm, BP neural network is trained.
5., based on a wisdom energy energy conserving system for neural network, it is characterized in that, comprising:
Access gateway, for obtaining the energy consumption data of bottom hardware, and is sent to wisdom energy management platform by described energy consumption data;
Wisdom energy management platform, for receiving the described energy consumption data of bottom hardware, utilizes trained BP neural network to obtain the approximate optimal solution of energy consumption data, according to described approximate optimal solution and the load threshold pre-set, determines energy saving optimizing strategy; Described energy saving optimizing strategy is sent to described access gateway;
Access gateway, also for receiving described energy saving optimizing strategy, according to described energy saving optimizing strategy, regulates the controling parameters of bottom hardware, to optimize the energy consumption of bottom hardware.
6. the wisdom energy energy conserving system based on neural network according to claim 5, it is characterized in that, also comprise bottom hardware, described bottom hardware comprises sensor, actuating unit, measuring instrument.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510526523.4A CN105045096A (en) | 2015-08-26 | 2015-08-26 | Intelligent energy saving method based on neural network and system thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510526523.4A CN105045096A (en) | 2015-08-26 | 2015-08-26 | Intelligent energy saving method based on neural network and system thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105045096A true CN105045096A (en) | 2015-11-11 |
Family
ID=54451716
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510526523.4A Pending CN105045096A (en) | 2015-08-26 | 2015-08-26 | Intelligent energy saving method based on neural network and system thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105045096A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110138604A (en) * | 2019-04-29 | 2019-08-16 | 浙江大学 | A kind of Internet of things hardware platform automatic generation method towards multi-performance index |
CN113448249A (en) * | 2021-06-28 | 2021-09-28 | 南京天溯自动化控制***有限公司 | Energy-saving diagnosis method and device for energy system, storage medium and electronic equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030200075A1 (en) * | 2002-04-19 | 2003-10-23 | Computer Associates Think, Inc. | Automatic model maintenance through local nets |
CN101782743A (en) * | 2010-02-11 | 2010-07-21 | 浙江大学 | Neural network modeling method and system |
CN102063327A (en) * | 2010-12-15 | 2011-05-18 | 中国科学院深圳先进技术研究院 | Application service scheduling method with power consumption consciousness for data center |
CN102999034A (en) * | 2012-12-13 | 2013-03-27 | 北京天地互连信息技术有限公司 | Industrial monitoring system based on Institute of Electrical and Electronics Engineers (IEEE) 1888 standard |
CN102999035A (en) * | 2012-12-13 | 2013-03-27 | 北京天地互连信息技术有限公司 | Intelligent building energy-saving system based on Institute of Electrical and Electronics Engineers (IEEE) 1888 standard |
CN103428282A (en) * | 2013-08-06 | 2013-12-04 | 浪潮(北京)电子信息产业有限公司 | On-line energy-saving control method and device for cloud computing data center |
CN104503847A (en) * | 2015-01-22 | 2015-04-08 | 浪潮(北京)电子信息产业有限公司 | Data center energy saving method and device |
-
2015
- 2015-08-26 CN CN201510526523.4A patent/CN105045096A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030200075A1 (en) * | 2002-04-19 | 2003-10-23 | Computer Associates Think, Inc. | Automatic model maintenance through local nets |
CN101782743A (en) * | 2010-02-11 | 2010-07-21 | 浙江大学 | Neural network modeling method and system |
CN102063327A (en) * | 2010-12-15 | 2011-05-18 | 中国科学院深圳先进技术研究院 | Application service scheduling method with power consumption consciousness for data center |
CN102999034A (en) * | 2012-12-13 | 2013-03-27 | 北京天地互连信息技术有限公司 | Industrial monitoring system based on Institute of Electrical and Electronics Engineers (IEEE) 1888 standard |
CN102999035A (en) * | 2012-12-13 | 2013-03-27 | 北京天地互连信息技术有限公司 | Intelligent building energy-saving system based on Institute of Electrical and Electronics Engineers (IEEE) 1888 standard |
CN103428282A (en) * | 2013-08-06 | 2013-12-04 | 浪潮(北京)电子信息产业有限公司 | On-line energy-saving control method and device for cloud computing data center |
CN104503847A (en) * | 2015-01-22 | 2015-04-08 | 浪潮(北京)电子信息产业有限公司 | Data center energy saving method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110138604A (en) * | 2019-04-29 | 2019-08-16 | 浙江大学 | A kind of Internet of things hardware platform automatic generation method towards multi-performance index |
CN113448249A (en) * | 2021-06-28 | 2021-09-28 | 南京天溯自动化控制***有限公司 | Energy-saving diagnosis method and device for energy system, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111176929A (en) | Edge federal learning-oriented high-energy-efficiency calculation communication joint optimization method | |
CN110851774B (en) | Leakage estimation method for urban water supply network | |
CN114265631B (en) | Mobile edge computing intelligent unloading method and device based on federation element learning | |
CN114885340B (en) | Ultra-dense wireless network power distribution method based on deep migration learning | |
CN105490269A (en) | WAMS measurement-based multi-region power system state estimation method and system | |
CN113675947A (en) | Power transmission side equipment state monitoring method of power transmission gateway and power transmission gateway | |
CN102065510A (en) | Wireless sensor network node adaptive power control system and method based on fuzzy logic | |
CN105045096A (en) | Intelligent energy saving method based on neural network and system thereof | |
CN104503847A (en) | Data center energy saving method and device | |
CN116346819A (en) | Industrial Internet system based on cloud edge cooperation | |
CN113242066B (en) | Multi-cell large-scale MIMO communication intelligent power distribution method | |
CN103267871A (en) | Wind speed monitoring system based on ZigBee technology | |
CN116614195A (en) | Electric carbon calculation intelligent fusion terminal based on edge container and time synchronization method | |
CN109578209A (en) | A kind of complicated wind-powered electricity generation power generation parameter control system based on embedded Control combination Internet of Things | |
CN106412935B (en) | A kind of network topology structure method for building up based on Complex Networks Theory | |
CN111669767B (en) | Sensor network dynamic deployment method | |
CN114997422A (en) | Grouping type federal learning method of heterogeneous communication network | |
Strelkovskaya et al. | Comparative analysis of the methods of wavelet-and spline-extrapolation in problems of predicting self-similar traffic | |
CN103402276A (en) | System and method for efficiently transmitting mass sensing data of internet of things | |
Cai et al. | Urban water supply network monitoring and management platform based on wireless sensor network | |
CN112601246A (en) | Optimal power distribution algorithm in multi-node cooperative wireless vision sensor network | |
CN112486667A (en) | Method and device for accurately processing data based on edge calculation | |
CN104217372A (en) | Power supply path tracking method suitable for large-scale complex power distribution network | |
CN111082522A (en) | Distribution network state monitoring and fault processing system based on ubiquitous power Internet of things | |
CN105517190B (en) | Adaptive wireless data sharing method and system for mobile robot cooperation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151111 |
|
RJ01 | Rejection of invention patent application after publication |