CN108833227A - A kind of smart home communication optimization scheduling system and method based on edge calculations - Google Patents
A kind of smart home communication optimization scheduling system and method based on edge calculations Download PDFInfo
- Publication number
- CN108833227A CN108833227A CN201810635338.2A CN201810635338A CN108833227A CN 108833227 A CN108833227 A CN 108833227A CN 201810635338 A CN201810635338 A CN 201810635338A CN 108833227 A CN108833227 A CN 108833227A
- Authority
- CN
- China
- Prior art keywords
- optimization
- communication optimization
- zigbee
- smart home
- intelligent household
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Automation & Control Theory (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present invention provides a kind of, and the smart home communication optimization based on edge calculations dispatches system and method, which includes:Intelligent household terminal domain:Including one of ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal or a variety of;Edge access layer:Comprising one of ZigBee router, operator base station and wireless base station or a variety of;Internet access layer realizes the access of operator base station and wireless base station;Home gateway access layer:Including several home gateways;Core layer:Including at least one Optimized Operation device, realizes and the Optimized Operation from ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal is requested;Smart home communication optimization functional analysis device:Including edge calculations smart home communication optimization service core cloud, the core processing to the Optimized Operation information from ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal is realized.
Description
Technical field
The present invention relates to smart homes and edge calculations technical field, and in particular to a kind of intelligence based on edge calculations
Household communication optimization dispatches system and method.
Background technique
Smart home is the embodiment of the instrumentation under the influence of internet.Smart home will be in family by technology of Internet of things
Various equipment (such as audio & video equipment, lighting system, curtain control, airconditioning control, security system, Digital Theater System, shadow
Sound server, shadow cabinet system, network home appliance etc.) it connects together, control is provided.
And as Internet of Things is grown rapidly, the quantity of edge termination equipment increases sharply, while edge termination equipment is produced
Raw data volume has reached damp byte (ZB) rank.Centralized data processing cannot be effectively treated caused by edge termination equipment
Mass data, edge calculations are generally regarded as one of the main trend of Next Generation of Digital transition by industry.Mobile edge meter
Calculate (Mobile Edge Computing, MEC) be the part calculating task of traditional cloud computing platform is moved into input field, and
Traditional business and Internet service are subjected to depth integration, reduce the end-to-end time delay that traditional business is delivered, and then bring operation
The running of quotient brings new mode, and establishes completely new industrial chain and the ecosphere.In this case, the side in face of being increasingly urgent to
Edge calculates and smart home growth requirement, and the smart home communication optimization based on edge calculations is dispatched for edge calculations and intelligence
The rapid sustainable development of energy household is of great significance.
But with edge calculations and the rapid growth of smart home business, with the high latency of generation, high flow capacity at
Originally, the problems such as non real-time, becomes increasingly conspicuous.Existing cloud computing system has the characteristics such as delay height, real-time difference, does not fully take into account
High latency, high flow capacity cost, non real-time etc. problem.So letter one kind to be developed it is new system and method it is above-mentioned to solve
Problem.
Summary of the invention
In a first aspect, the present invention provides a kind of smart home communication optimization scheduling system based on edge calculations, the system
Including:
Intelligent household terminal domain:Including in ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal
It is one or more;
Edge access layer:Include one of ZigBee router, operator base station and wireless base station or a variety of, realization
The access in intelligent household terminal domain;
Internet access layer realizes the access of operator base station and wireless base station;
Home gateway access layer:Including several home gateways, the access from ZigBee router and internet is realized;
Core layer:Including at least one Optimized Operation device, realize to mobile from ZigBee intelligent household terminal, mobile phone
The request of the Optimized Operation of terminal and computer mobile terminal;
Smart home communication optimization functional analysis device:It is real including edge calculations smart home communication optimization service core cloud
Now to the core of the Optimized Operation information from ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal at
Reason.
With reference to first aspect, in a first possible implementation of that first aspect, the ZigBee intelligent household terminal
ZigBee router is linked by ZigBee-network;The mobile terminal of mobile telephone and computer mobile terminal pass through operation respectively
Quotient's network and wireless network access carrier base station and wireless base station;The operator base station and wireless base station access it is described because
Front yard gateway accessing layer of getting home is accessed after special net access layer;The ZigBee router is linked into home gateway access layer;The family
Optimized Operation device of the front yard gateway accessing to core layer;The Optimized Operation device is linked into the smart home communication optimization function
The edge calculations smart home communication optimization service core cloud of analyzer.
Second aspect, the present invention provide a kind of smart home communication optimization dispatching method based on edge calculations, this method
Include the following steps:
1) intelligent household terminal domain issues the request of ZigBee intelligent household terminal communication optimization;
2) the ZigBee intelligent household terminal communication optimization request reaches side smart home communication optimization function by transmission
Edge computational intelligence household communication optimization service core cloud in energy analyzer;The edge calculations smart home communication optimization clothes
Business core cloud processing ZigBee intelligent household terminal communication optimization request;And ZigBee intelligent household terminal leads to by treated
Letter optimization request result feeds back to the Optimized Operation device of core layer;
3) by treated, ZigBee intelligent household terminal communication optimization request results return to house to the Optimized Operation device
The home gateway of front yard gateway accessing layer;
4) by treated, ZigBee intelligent household terminal communication optimization request results return to edge to the home gateway
The ZigBee router of access layer returns to the operator base station and wireless base station by internet layer;The ZigBee
Router or the operator base station and wireless base station will treated ZigBee intelligent household terminal communication optimization request results
It returns to ZigBee intelligent household terminal and implements the ZigBee intelligent household terminal communication optimization request after optimization.
In conjunction with second aspect, in second aspect in the first possible implementation, intelligence man described in the step 1)
Occupying terminal field and issuing letter optimization request is the meter that the ZigBee intelligent household terminal issued and handled that part moves to terminal
It calculates, the ZigBee intelligent household terminal after storage and network believes optimization request all or mobile by mobile terminal of mobile telephone or computer
The ZigBee intelligent household terminal communication optimization request that terminal issues.
In conjunction with the first implementation of second aspect, in second of second aspect possible implementation, the place
The communication of ZigBee intelligent household terminal is excellent including treated for ZigBee intelligent household terminal communication optimization request results after reason
Change request and the remaining task requests result in addition to the communication optimizations tasks such as the calculating, storage and network for partially moving to terminal.
In conjunction with second aspect and above-mentioned possible implementation, in second aspect in the third possible implementation, institute
Stating the processing ZigBee intelligent household terminal communication optimization request of smart home communication optimization functional analysis device includes:ZigBee intelligence
Energy household communication optimization request is received, is asked with hyperspace deep-cycle neural network analysis of strategies smart home communication optimization
It asks, recommendation results export and hyperspace deep-cycle neural network strategy semi-supervised learning.
In conjunction with second aspect and above-mentioned possible implementation, in the 4th kind of possible implementation of second aspect, institute
State smart home communication optimization functional analysis device processing ZigBee intelligent household terminal communication optimization request the specific steps are:
1) request of ZigBee smart home communication optimization receives to obtain and summarize
Every preset time active reporting and periodically be asked mechanism obtain smart home communication optimization request, and by this
A little information are summarized;
2) iteration initial parameter is set
It is 50 that iteration maximum algebra d, which is arranged,;
3) current iteration number k adds 1
Current iteration number increases by 1 time namely k+1, k≤d;
4) with the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization
With the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization;
5) each depth optimization analysis initial results acquisition summarizes
Smart home communication optimization request recommendation results are obtained and summarized;
6) hyperspace deep-cycle Neural Network Optimization strategy semi-supervised learning
Semi-supervised learning is carried out in conjunction with tangent expert decision-making library deep-cycle neural network semi-supervised learning method;
7) judge whether to meet depth optimization assay condition
According to hyperspace, Recognition with Recurrent Neural Network, deep learning, probability theory, biology, operational research, intelligent optimization, machine
Depth optimization assay condition, that is, evaluation function (see formula 1-2) of the device theories of learning judged, when being unsatisfactory for depth optimization
It should continue iteration when assay condition;
8) current iteration number adds 1
Current iteration number increases by 1 time namely k+1, k≤d;
9) with the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization
With the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization;
10) each depth optimization analysis result acquisition summarizes
It every preset time active reporting and is periodically asked mechanism acquisition and summarizes smart home communication optimization requirement analysis
Optimum results information;
11) meet current iteration number greater than maximum number of iterations
It is greater than maximum number of iterations evaluation condition according to current iteration number to be judged, is jumped to 6) when being unsatisfactory for
Continue iteration, terminates when meeting.
Step 6) the hyperspace deep-cycle Neural Network Optimization strategy semi-supervised learning and step 7) judge whether
Meet depth optimization assay condition to specifically include:
Storage model:
Joint Andrei Kolmogorov evaluation function:
I=1,2 ... m, j=1,2 ... n, t=1,2 ... p, k=1,2 ..., d, ε ∈ (0,1) (1-2)
Deep-cycle Neural Network Optimization function:
λ, β ∈ (0,1) ,+β=1 λ (1-3)
Wherein k of the formula (1-2) into formula (1-6) indicates kth time iteration, and wherein k must satisfy k≤d condition, need to meet k
=1,2 ..., the condition of d;Wherein, 1,2, L be hyperspace;
In formula (1-3), (1-4) and (1-5)Mainly include:WithBoth sides information vector, formula (1-
2), in (1-3), (1-4), (1-5) and (1-6) LmaxG、CmaxG、MmaxG、MmaxK、MminK、 MminGThe respectively current kth time iteration time delay of depth optimization, current kth time average delay, current
Kth time flow cost, current kth time average flow rate cost, historical information time delay maximum value, historical information flow cost are maximum
Value, current kth time information vector, history maximum information vector, current kth time maximum information vector, the minimum letter of current kth time
Cease vector ,+1 information vector of kth ,+1 tangent experts database semi-supervised learning factor of kth, kth+1 the reward factor, history
Minimal information vector, so that this algorithm chooses local optimum.
The smart home communication optimization, which dispatches system, has low latency, low discharge cost, the advantages such as in real time, cooperates this to be
The method of system can effectively realize the above-mentioned advantage of the system, and the system is made to have stronger competitiveness.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of the application, attached drawing needed in the embodiment will be made below
Simply introduce, it should be apparent that, for those of ordinary skills, in the premise of not making the creative labor property
Under, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is that the depth of one of specific embodiment of method that the application smart home communication optimization dispatches system is excellent
Change analysis strategy execution flow chart;
Fig. 2 is the schematic diagram of storage model.
Specific embodiment
To make those skilled in the art more fully understand technical solution of the present invention, with reference to the accompanying drawing to the present invention
A kind of smart home communication optimization scheduling system and method based on edge calculations of offer is described in detail.
It elaborates below to embodiments herein.
In one embodiment of the invention, a kind of smart home communication optimization scheduling based on edge calculations is provided
System, the system include:
Intelligent household terminal domain:Including in ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal
It is one or more;
Edge access layer:Include one of ZigBee router, operator base station and wireless base station or a variety of, realization
The access in intelligent household terminal domain;
Internet access layer realizes the access of operator base station and wireless base station;
Home gateway access layer:Including several home gateways, the access from ZigBee router and internet is realized;
Core layer:Including at least one Optimized Operation device, realize to mobile from ZigBee intelligent household terminal, mobile phone
The request of the Optimized Operation of terminal and computer mobile terminal;
Smart home communication optimization functional analysis device:It is real including edge calculations smart home communication optimization service core cloud
Now to the core of the Optimized Operation information from ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal at
Reason, smart home communication optimization functional analysis device are mainly completed to request to be analyzed and processed to smart home communication optimization, and will
Analysis treated relevant information is transmitted to corresponding analysis is as a result, also include that processing is whole except ZigBee smart home is moved to
The services such as remainder calculating, storage and network outside end.
In a second embodiment of the present invention, the ZigBee intelligent household terminal is arrived by ZigBee network insertion
ZigBee router;The mobile terminal of mobile telephone and computer mobile terminal pass through carrier network and wireless network access respectively
Operator base station and wireless base station;It accesses and gets home behind the operator base station and the wireless base station access internet access layer
Front yard gateway accessing layer;The ZigBee router is linked into home gateway access layer;The home gateway is linked into core layer
Optimized Operation device;The Optimized Operation device is linked into the edge calculations intelligence of the smart home communication optimization functional analysis device
Household communication optimization service core cloud.
In third embodiment of the invention, it is excellent that the present invention provides a kind of smart home communication based on edge calculations
Change dispatching method, this method comprises the following steps:
1) intelligent household terminal domain issues the request of ZigBee intelligent household terminal communication optimization;
2) the ZigBee intelligent household terminal communication optimization request reaches side smart home communication optimization function by transmission
Edge computational intelligence household communication optimization service core cloud in energy analyzer;The edge calculations smart home communication optimization clothes
Business core cloud processing ZigBee intelligent household terminal communication optimization request;And ZigBee intelligent household terminal leads to by treated
Letter optimization request result feeds back to the Optimized Operation device of core layer;
3) by treated, ZigBee intelligent household terminal communication optimization request results return to house to the Optimized Operation device
The home gateway of front yard gateway accessing layer;
4) by treated, ZigBee intelligent household terminal communication optimization request results return to edge to the home gateway
The ZigBee router of access layer returns to the operator base station and wireless base station by internet layer;The ZigBee
Router or the operator base station and wireless base station will treated ZigBee intelligent household terminal communication optimization request results
It returns to ZigBee intelligent household terminal and implements the ZigBee intelligent household terminal communication optimization request after optimization.
In the 4th embodiment of the invention, intelligent household terminal domain described in the step 1) issues letter optimization and asks
It asks after issuing for the ZigBee intelligent household terminal and handle the calculating, storage and network that part moves to terminal
The ZigBee intelligence that ZigBee intelligent household terminal is believed optimization request all or issued by mobile terminal of mobile telephone or computer mobile terminal
It can the request of household terminal communication optimization.
In the 5th embodiment of the invention, treated the ZigBee intelligent household terminal communication optimization request
As a result including treated, ZigBee intelligent household terminal communication optimization is requested and except calculating, the storage for partially moving to terminal
With the remaining task requests result outside the communication optimizations task such as network.
In the 6th embodiment of the invention, the smart home communication optimization functional analysis device handles ZigBee intelligence
Energy household terminal communication optimization is requested:The request of ZigBee smart home communication optimization receives, with hyperspace deep-cycle
The request of neural network analysis of strategies smart home communication optimization, recommendation results output and hyperspace deep-cycle neural network
Tactful semi-supervised learning.Wherein, each smart home communication optimization solicited message mainly includes:Time delay L, flow cost C.Pass through
Analysis smart home communication optimization request realize for each smart home communication optimization request time delay L, flow cost C into
Row depth optimization, hyperspace deep-cycle neural network strategy semi-supervised learning are realized and provide recommendation results.
As shown in Figure 1, in the 7th embodiment of the invention, at the smart home communication optimization functional analysis device
Manage ZigBee intelligent household terminal communication optimization request the specific steps are:
1) request of ZigBee smart home communication optimization receives to obtain and summarize
Every preset time active reporting and periodically be asked mechanism obtain smart home communication optimization request, and by this
A little information are summarized;
2) iteration initial parameter is set
It is 50 that iteration maximum algebra d, which is arranged,;
3) current iteration number k adds 1
Current iteration number increases by 1 time namely k+1, k≤d;
4) with the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization
With the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization;
5) each depth optimization analysis initial results acquisition summarizes
Smart home communication optimization request recommendation results are obtained and summarized;
6) hyperspace deep-cycle Neural Network Optimization strategy semi-supervised learning
Semi-supervised learning is carried out in conjunction with tangent expert decision-making library deep-cycle neural network semi-supervised learning method;
7) judge whether to meet depth optimization assay condition
According to hyperspace, Recognition with Recurrent Neural Network, deep learning, probability theory, biology, operational research, intelligent optimization, machine
Depth optimization assay condition, that is, evaluation function (see formula 1-2) of the device theories of learning judged, when being unsatisfactory for depth optimization
It should continue iteration when assay condition;
8) current iteration number adds 1
Current iteration number increases by 1 time namely k+1, k≤d;
9) with the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization
With the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization;
10) each depth optimization analysis result acquisition summarizes
It every preset time active reporting and is periodically asked mechanism acquisition and summarizes smart home communication optimization requirement analysis
Optimum results information;
11) meet current iteration number greater than maximum number of iterations
It is greater than maximum number of iterations evaluation condition according to current iteration number to be judged, is jumped to 6) when being unsatisfactory for
Continue iteration, terminates when meeting.
Depth optimization thought is that each smart home communication optimization solicited message is judged and analyzed, each smart home
Communication optimization request has different priority levels.The present invention requests smart home communication optimization with depth optimization assay
The depth optimization strategy of Function Optimization is analyzed.In conjunction with tangent expert decision-making library deep-cycle neural network semi-supervised learning
Numerous advantages such as method realization low latency of the present invention, low discharge cost, real-time.The algorithm is passively collected using actively simultaneous in real time
Smart home communication optimization solicited message is simultaneously analyzed in real time, hence it is evident that optimizes the time delay of each smart home communication optimization request results
L, flow cost C etc. index.
In the 8th embodiment of the invention, step 6) the hyperspace deep-cycle Neural Network Optimization strategy
Semi-supervised learning and step 7) judge whether that meeting depth optimization assay condition specifically includes:
Storage model (as shown in Figure 2):
Joint Andrei Kolmogorov evaluation function:
I=1,2 ... m, j=1,2 ... n, t=1,2 ... p, k=1,2 ..., d, ε ∈ (0,1) (1-2)
Deep-cycle Neural Network Optimization function:
λ, β ∈ (0,1) ,+β=1 λ (1-3)
Wherein k of the formula (1-2) into formula (1-6) indicates kth time iteration, and wherein k must satisfy k≤d condition, need to meet k
=1,2 ..., the condition of d;Wherein, 1,2, L be hyperspace;
In formula (1-3), (1-4) and (1-5)Mainly include:WithBoth sides information vector, formula (1-
2), in (1-3), (1-4), (1-5) and (1-6) LmaxG、CmaxG、MmaxG、MmaxK、MminK、 MminGThe respectively current kth time iteration time delay of depth optimization, current kth time average delay, current
Kth time flow cost, current kth time average flow rate cost, historical information time delay maximum value, historical information flow cost are maximum
Value, current kth time information vector, history maximum information vector, current kth time maximum information vector, the minimum letter of current kth time
Cease vector ,+1 information vector of kth ,+1 tangent experts database semi-supervised learning factor of kth, kth+1 the reward factor, history
Minimal information vector, so that this algorithm chooses local optimum.
The smart home communication optimization, which dispatches system, has low latency, low discharge cost, the advantages such as in real time, cooperates this to be
The method of system can effectively realize the above-mentioned advantage of the system, and the system is made to have stronger competitiveness.
Same and similar part may refer to each other between each embodiment in this specification.Invention described above
Embodiment is not intended to limit the scope of the present invention..
It is understood that the principle that embodiment of above is intended to be merely illustrative of the present and the exemplary reality that uses
Mode is applied, however the present invention is not limited thereto.For those skilled in the art, the present invention is not being departed from
Spirit and essence in the case where, various changes and modifications can be made therein, these variations and modifications are also considered as protection of the invention
Range.
Claims (8)
1. a kind of smart home communication optimization based on edge calculations dispatches system, which includes:
Intelligent household terminal domain:Including one of ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal
Or it is a variety of;
Edge access layer:Include one of ZigBee router, operator base station and wireless base station or a variety of, the intelligent family of realization
Occupy the access of terminal field;
Internet access layer realizes the access of operator base station and wireless base station;
Home gateway access layer:Including several home gateways, the access from ZigBee router and internet is realized;
Core layer:Including at least one Optimized Operation device, realize to from ZigBee intelligent household terminal, mobile terminal of mobile telephone and
The Optimized Operation of computer mobile terminal is requested;
Smart home communication optimization functional analysis device:Including edge calculations smart home communication optimization service core cloud, realization pair
The core processing of Optimized Operation information from ZigBee intelligent household terminal, mobile terminal of mobile telephone and computer mobile terminal.
2. system according to claim 1, it is characterised in that:The ZigBee intelligent household terminal passes through ZigBee-network
It is linked into ZigBee router;The mobile terminal of mobile telephone and computer mobile terminal pass through carrier network and wireless network respectively
Access carrier base station and wireless base station;The operator base station and wireless base station are linked into after accessing the internet access layer
Home gateway access layer;The ZigBee router is linked into home gateway access layer;The home gateway is linked into core layer
Optimized Operation device;The Optimized Operation device is linked into the edge calculations intelligence of the smart home communication optimization functional analysis device
Household communication optimization service core cloud.
3. a kind of smart home communication optimization dispatching method based on edge calculations, which is characterized in that this method includes following step
Suddenly:
1) intelligent household terminal domain issues the request of ZigBee intelligent household terminal communication optimization;
2) the ZigBee intelligent household terminal communication optimization request reaches side smart home communication optimization function point by transmission
Edge computational intelligence household communication optimization service core cloud in parser;The edge calculations smart home communication optimization service core
Cloud handles the request of ZigBee intelligent household terminal communication optimization;And ZigBee intelligent household terminal communication optimization is asked by treated
Result is asked to feed back to the Optimized Operation device of core layer;
3) by treated, ZigBee intelligent household terminal communication optimization request results return to home network to the Optimized Operation device
Close the home gateway of access layer;
4) by treated, ZigBee intelligent household terminal communication optimization request results return to edge access to the home gateway
The ZigBee router of layer returns to the operator base station and wireless base station by internet layer;The ZigBee router
Or ZigBee intelligent household terminal communication optimization request results return to by treated for the operator base station and wireless base station
ZigBee intelligent household terminal simultaneously implements the ZigBee intelligent household terminal communication optimization request after optimization.
4. according to the method described in claim 3, it is characterized in that, intelligent household terminal domain described in the step 1) issues letter
Optimization request is after the ZigBee intelligent household terminal issues and handles the calculating, storage and network that part moves to terminal
The ZigBee intelligence that ZigBee intelligent household terminal is believed optimization request all or issued by mobile terminal of mobile telephone or computer mobile terminal
It can the request of household terminal communication optimization.
5. according to the method described in claim 3, it is characterized in that, treated ZigBee intelligent household terminal communication is excellent
Change the request results ZigBee intelligent household terminal communication optimization request that includes that treated and except partially move to terminal calculating,
Remaining task requests result outside the communication optimizations task such as storage and network.
6. according to the method described in claim 3, it is characterized in that, the smart home communication optimization functional analysis device is handled
ZigBee intelligent household terminal communication optimization is requested:The request of ZigBee smart home communication optimization receives, with hyperspace
The request of deep-cycle neural network analysis of strategies smart home communication optimization, recommendation results output and hyperspace deep-cycle mind
Through network strategy semi-supervised learning.
7. according to the method described in claim 3, it is characterized in that, the smart home communication optimization functional analysis device is handled
ZigBee intelligent household terminal communication optimization request the specific steps are:
1) request of ZigBee smart home communication optimization receives to obtain and summarize
It every preset time active reporting and is periodically asked mechanism and obtains the request of smart home communication optimization, and by these information
Summarized;
2) iteration initial parameter is set
It is 50 that iteration maximum algebra d, which is arranged,;
3) current iteration number k adds 1
Current iteration number increases by 1 time namely k+1, k≤d;
4) with the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization
With the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization;
5) each depth optimization analysis initial results acquisition summarizes
Smart home communication optimization request recommendation results are obtained and summarized;
6) hyperspace deep-cycle Neural Network Optimization strategy semi-supervised learning
Semi-supervised learning is carried out in conjunction with tangent expert decision-making library deep-cycle neural network semi-supervised learning method;
7) judge whether to meet depth optimization assay condition
According to hyperspace, Recognition with Recurrent Neural Network, deep learning, probability theory, biology, operational research, intelligent optimization, machine learning
Theoretical depth optimization assay condition, that is, evaluation function (see formula 1-2) is judged, is commented when being unsatisfactory for depth optimization analysis
It should continue iteration when valence condition;
8) current iteration number adds 1
Current iteration number increases by 1 time namely k+1, k≤d;
9) with the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization
With the request of hyperspace deep-cycle neural network semi-supervised learning analysis of strategies smart home communication optimization;
10) each depth optimization analysis result acquisition summarizes
It every preset time active reporting and is periodically asked mechanism acquisition and summarizes the optimization of smart home communication optimization requirement analysis
Result information;
11) meet current iteration number greater than maximum number of iterations
According to current iteration number be greater than maximum number of iterations evaluation condition judged, jumped to when being unsatisfactory for 6) continue into
Row iteration terminates when meeting.
8. the method according to the description of claim 7 is characterized in that step 6) the hyperspace deep-cycle neural network is excellent
Change tactful semi-supervised learning and step 7) judges whether that meeting depth optimization assay condition specifically includes:
Storage model:
Joint Andrei Kolmogorov evaluation function:
Deep-cycle Neural Network Optimization function:
λ, β ∈ (0,1) ,+β=1 λ (1-3)
Wherein k of the formula (1-2) into formula (1-6) indicates kth time iteration, and wherein k must satisfy k≤d condition, need to meet k=1,
2 ..., the condition of d;Wherein, 1,2, L be hyperspace;
M in formula (1-3), (1-4) and (1-5)ijt kMainly include:WithBoth sides information vector, formula (1-2), (1-
3), in (1-4), (1-5) and (1-6) LmaxG、CmaxG、MmaxG、MmaxK、MminK、 MminGThe respectively current kth time iteration time delay of depth optimization, current kth time average delay, current
Kth time flow cost, current kth time average flow rate cost, historical information time delay maximum value, historical information flow cost are maximum
Value, current kth time information vector, history maximum information vector, current kth time maximum information vector, current kth time minimal information
Vector ,+1 information vector of kth ,+1 tangent experts database semi-supervised learning factor of kth ,+1 reward factor of kth, history are minimum
Information vector, so that this algorithm chooses local optimum.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810635338.2A CN108833227B (en) | 2018-06-20 | 2018-06-20 | Intelligent home communication optimal scheduling system and method based on edge calculation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810635338.2A CN108833227B (en) | 2018-06-20 | 2018-06-20 | Intelligent home communication optimal scheduling system and method based on edge calculation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108833227A true CN108833227A (en) | 2018-11-16 |
CN108833227B CN108833227B (en) | 2021-03-19 |
Family
ID=64142935
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810635338.2A Active CN108833227B (en) | 2018-06-20 | 2018-06-20 | Intelligent home communication optimal scheduling system and method based on edge calculation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108833227B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110262340A (en) * | 2019-06-20 | 2019-09-20 | 上海禾视信息技术有限公司 | A kind of Internet of Things access and monitoring method based on edge calculations |
CN110493313A (en) * | 2019-07-19 | 2019-11-22 | 北京邮电大学 | A kind of method and system of the dispatch service use-case in based on mobile edge calculations network |
CN112040189A (en) * | 2020-09-01 | 2020-12-04 | 浙江大华技术股份有限公司 | Monitoring method and system of front-end equipment and storage medium |
CN112437086A (en) * | 2020-11-23 | 2021-03-02 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring monitoring data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101860978A (en) * | 2010-05-14 | 2010-10-13 | 南京邮电大学 | Internet of things system structure |
US8782395B1 (en) * | 2011-09-29 | 2014-07-15 | Riverbed Technology, Inc. | Monitoring usage of WAN optimization devices integrated with content delivery networks |
CN105404169A (en) * | 2015-12-29 | 2016-03-16 | 上海大学 | Central control system of smart home and control method |
CN106921702A (en) * | 2015-12-25 | 2017-07-04 | 中国电力科学研究院 | It is a kind of based on service-oriented power distribution network information physical system |
CN107404733A (en) * | 2017-08-22 | 2017-11-28 | 山东省计算中心(国家超级计算济南中心) | A kind of 5G method of mobile communication and system based on MEC and layering SDN |
CN108023840A (en) * | 2017-12-12 | 2018-05-11 | 中国联合网络通信集团有限公司 | OVS network traffics accelerate optimization method and OVS network traffics to accelerate optimization system |
-
2018
- 2018-06-20 CN CN201810635338.2A patent/CN108833227B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101860978A (en) * | 2010-05-14 | 2010-10-13 | 南京邮电大学 | Internet of things system structure |
US8782395B1 (en) * | 2011-09-29 | 2014-07-15 | Riverbed Technology, Inc. | Monitoring usage of WAN optimization devices integrated with content delivery networks |
CN106921702A (en) * | 2015-12-25 | 2017-07-04 | 中国电力科学研究院 | It is a kind of based on service-oriented power distribution network information physical system |
CN105404169A (en) * | 2015-12-29 | 2016-03-16 | 上海大学 | Central control system of smart home and control method |
CN107404733A (en) * | 2017-08-22 | 2017-11-28 | 山东省计算中心(国家超级计算济南中心) | A kind of 5G method of mobile communication and system based on MEC and layering SDN |
CN108023840A (en) * | 2017-12-12 | 2018-05-11 | 中国联合网络通信集团有限公司 | OVS network traffics accelerate optimization method and OVS network traffics to accelerate optimization system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110262340A (en) * | 2019-06-20 | 2019-09-20 | 上海禾视信息技术有限公司 | A kind of Internet of Things access and monitoring method based on edge calculations |
CN110493313A (en) * | 2019-07-19 | 2019-11-22 | 北京邮电大学 | A kind of method and system of the dispatch service use-case in based on mobile edge calculations network |
CN112040189A (en) * | 2020-09-01 | 2020-12-04 | 浙江大华技术股份有限公司 | Monitoring method and system of front-end equipment and storage medium |
CN112437086A (en) * | 2020-11-23 | 2021-03-02 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring monitoring data |
CN112437086B (en) * | 2020-11-23 | 2022-07-29 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring monitoring data |
Also Published As
Publication number | Publication date |
---|---|
CN108833227B (en) | 2021-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108833227A (en) | A kind of smart home communication optimization scheduling system and method based on edge calculations | |
CN107690176B (en) | Network selection method based on Q learning algorithm | |
CN108924198A (en) | A kind of data dispatching method based on edge calculations, apparatus and system | |
CN111010294A (en) | Electric power communication network routing method based on deep reinforcement learning | |
CN113435472A (en) | Vehicle-mounted computing power network user demand prediction method, system, device and medium | |
CN105379412B (en) | A kind of system and method controlling multiple radio access nodes | |
CN109815389A (en) | Using the node matching method, apparatus and computer equipment of regulation engine | |
CN102567851B (en) | Safely-sensed scientific workflow data layout method under cloud computing environment | |
CN110011863A (en) | A kind of network bandwidth resources equalization scheduling method and device | |
CN114885420A (en) | User grouping and resource allocation method and device in NOMA-MEC system | |
Sun et al. | Accelerating convergence of federated learning in MEC with dynamic community | |
CN110061881A (en) | A kind of energy consumption perception virtual network mapping algorithm based on Internet of Things | |
CN105991707A (en) | Multimedia interaction method, server and system thereof | |
CN108762846A (en) | Plug-in unit real-time recommendation method, server and computer readable storage medium | |
CN114154685A (en) | Electric energy data scheduling method in smart power grid | |
CN104822175B (en) | A kind of code migration method and system suitable for cellular network | |
CN103577899A (en) | Service composition method based on reliability prediction combined with QoS | |
CN106209990A (en) | The appreciable request scheduling method of cost under a kind of distribution strange land cloud data center | |
Liao et al. | Service composition based on niching particle swarm optimization in service overlay networks | |
CN106789163A (en) | A kind of network equipment power information monitoring method, device and system | |
CN113543160A (en) | 5G slice resource allocation method and device, computing equipment and computer storage medium | |
Xie et al. | A multiuser manufacturing resource service composition method based on the bees algorithm | |
Zhou et al. | Study on the evolutionary optimisation of the topology of network control systems | |
CN106210120B (en) | A kind of recommended method and its device of server | |
Chen et al. | A reinforcement learning based joint spectrum allocation and power control algorithm for D2D communication underlaying cellular networks |
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 |