CN108833227B - Intelligent home communication optimal scheduling system and method based on edge calculation - Google Patents
Intelligent home communication optimal scheduling system and method based on edge calculation Download PDFInfo
- Publication number
- CN108833227B CN108833227B CN201810635338.2A CN201810635338A CN108833227B CN 108833227 B CN108833227 B CN 108833227B CN 201810635338 A CN201810635338 A CN 201810635338A CN 108833227 B CN108833227 B CN 108833227B
- Authority
- CN
- China
- Prior art keywords
- intelligent home
- communication optimization
- terminal
- zigbee
- optimization
- 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
- 238000004891 communication Methods 0.000 title claims abstract description 152
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004364 calculation method Methods 0.000 title claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 177
- 239000010410 layer Substances 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 15
- 239000012792 core layer Substances 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims description 42
- 230000006870 function Effects 0.000 claims description 29
- 238000013433 optimization analysis Methods 0.000 claims description 25
- 238000011156 evaluation Methods 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 16
- 230000007246 mechanism Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000009191 jumping Effects 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000011160 research Methods 0.000 claims description 4
- 230000005012 migration Effects 0.000 claims description 3
- 238000013508 migration Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000283070 Equus zebra Species 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
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 invention provides an intelligent home communication optimal scheduling system and method based on edge calculation, wherein the system comprises: the intelligent home terminal domain: the intelligent home terminal comprises one or more of a ZigBee intelligent home terminal, a mobile phone terminal and a computer mobile terminal; an edge access layer: the system comprises one or more of a ZigBee router, an operator base station and a wireless base station; the Internet access layer realizes the access of the operator base station and the wireless base station; home gateway access layer: comprises a plurality of home gateways; core layer: the intelligent household terminal comprises at least one optimized scheduler, and optimized scheduling requests from a ZigBee intelligent household terminal, a mobile phone terminal and a computer mobile terminal are realized; the intelligent household communication optimization function analyzer: the method comprises an edge computing intelligent home communication optimization service core cloud, and core processing of optimized scheduling information from a ZigBee intelligent home terminal, a mobile phone terminal and a computer mobile terminal is achieved.
Description
Technical Field
The invention relates to the technical field of intelligent home and edge computing, in particular to an intelligent home communication optimal scheduling system and method based on edge computing.
Background
The intelligent home is embodied in an internet of things manner under the influence of the internet. The intelligent home connects various devices (such as audio and video devices, lighting systems, curtain control, air conditioner control, security systems, digital cinema systems, audio and video servers, video cabinet systems, network home appliances and the like) in the home together through the Internet of things technology to provide control.
With the rapid development of the internet of things, the number of edge terminal devices is rapidly increased, and meanwhile, the data volume generated by the edge terminal devices reaches the level of Zebra Bytes (ZB). Centralized data processing cannot effectively process the massive data generated by edge terminal devices, and edge computing has been generally recognized in the industry as one of the main trends of next-generation digital transformation. Mobile Edge Computing (MEC) is to migrate part of Computing tasks of a traditional cloud Computing platform to an access domain, and deeply merge traditional services with internet services, so as to reduce end-to-end time delay of traditional service delivery, bring a brand new mode to operation of operators, and establish a brand new industrial chain and ecosphere. Under the circumstance, in the face of increasingly urgent edge calculation and intelligent home development requirements, the intelligent home communication optimization scheduling based on the edge calculation has important significance for rapid and continuous development of the edge calculation and the intelligent home.
However, with the rapid growth of edge computing and smart home services, the problems of high delay, high traffic cost, non-real-time performance and the like are increasingly highlighted. The existing cloud computing system has the characteristics of high delay, poor real-time performance and the like, and the problems of high delay, high flow cost, non-real-time performance and the like are not fully considered. Therefore, a new system and method for solving the above problems have been desired.
Disclosure of Invention
In a first aspect, the present invention provides an intelligent home communication optimized scheduling system based on edge computing, including:
the intelligent home terminal domain: the intelligent home terminal comprises one or more of a ZigBee intelligent home terminal, a mobile phone terminal and a computer mobile terminal;
an edge access layer: the intelligent home terminal comprises one or more of a ZigBee router, an operator base station and a wireless base station, and realizes the access of an intelligent home terminal domain;
the Internet access layer realizes the access of the operator base station and the wireless base station;
home gateway access layer: the system comprises a plurality of home gateways, a ZigBee router and an Internet;
core layer: the intelligent household terminal comprises at least one optimized scheduler, and optimized scheduling requests from a ZigBee intelligent household terminal, a mobile phone terminal and a computer mobile terminal are realized;
the intelligent household communication optimization function analyzer: the method comprises an edge computing intelligent home communication optimization service core cloud, and core processing of optimized scheduling information from ZigBee intelligent home terminals, mobile phone terminals and computer mobile terminals is achieved.
With reference to the first aspect, in a first possible implementation manner of the first aspect, the ZigBee smart home terminal accesses the ZigBee router through a ZigBee network; the mobile phone mobile terminal and the computer mobile terminal are respectively accessed to an operator base station and a wireless base station through an operator network and a wireless network; the operator base station and the wireless base station are accessed to the home gateway access layer after being accessed to the Internet access layer; the ZigBee router is accessed to a home gateway access layer; the home gateway accesses to an optimization scheduler of a core layer; the optimization scheduler is accessed to an edge computing intelligent home communication optimization service core cloud of the intelligent home communication optimization function analyzer.
In a second aspect, the present invention provides an intelligent home communication optimization scheduling method based on edge calculation, including the following steps:
1) the intelligent home terminal domain sends out a ZigBee intelligent home terminal communication optimization request;
2) the ZigBee intelligent home terminal communication optimization request is transmitted to a marginal computing intelligent home communication optimization service core cloud in a marginal intelligent home communication optimization function analyzer; the edge computing intelligent home communication optimization service core cloud processes a ZigBee intelligent home terminal communication optimization request; feeding back the processed ZigBee intelligent home terminal communication optimization request result to an optimization scheduler of a core layer;
3) the optimization scheduler returns the processed communication optimization request result of the ZigBee intelligent home terminal to a home gateway of a home gateway access layer;
4) the home gateway returns the processed ZigBee intelligent home terminal communication optimization request result to a ZigBee router of an edge access layer or returns the processed ZigBee intelligent home terminal communication optimization request result to the operator base station and the wireless base station through an Internet layer; and the ZigBee router or the operator base station and the wireless base station return the processed ZigBee intelligent home terminal communication optimization request result to the ZigBee intelligent home terminal and implement the optimized ZigBee intelligent home terminal communication optimization request.
With reference to the second aspect, in a first possible implementation manner of the second aspect, in step 1), the sending of the communication optimization request by the intelligent home terminal domain is a communication optimization request sent by the ZigBee intelligent home terminal and used for processing a part of the calculation, storage and network migration to the terminal, of the ZigBee intelligent home terminal, or a communication optimization request sent by a mobile phone terminal or a computer mobile terminal of the ZigBee intelligent home terminal.
With reference to the first implementation manner of the second aspect, in a second possible implementation manner of the second aspect, the processed communication optimization request result of the ZigBee smart home terminal includes a processed communication optimization request of the ZigBee smart home terminal and a remaining task request result except for part of the communication optimization tasks migrated to the terminal, such as calculation, storage, and network.
With reference to the second aspect and the foregoing possible implementation manners, in a third possible implementation manner of the second aspect, the processing, by the smart home communication optimization function analyzer, the ZigBee smart home terminal communication optimization request includes: the method comprises the steps of receiving a ZigBee intelligent home communication optimization request, analyzing the intelligent home communication optimization request by a multi-dimensional space deep circulation neural network strategy, outputting a recommendation result and semi-supervised learning of the multi-dimensional space deep circulation neural network strategy.
With reference to the second aspect and the foregoing possible implementation manners, in a fourth possible implementation manner of the second aspect, the specific steps of processing the ZigBee smart home terminal communication optimization request by the smart home communication optimization function analyzer are as follows:
1) ZigBee intelligent home communication optimization request receiving, acquiring and summarizing
Actively reporting every preset time and regularly inquiring to obtain an intelligent home communication optimization request by a mechanism, and summarizing the information;
2) setting iteration initial parameters
Setting the iteration maximum algebra d as 50;
3) current iteration number k plus 1
The current iteration times are increased by 1 time, namely k +1, and k is less than or equal to d;
4) intelligent home communication optimization request analyzed through multidimensional space deep cycle neural network semi-supervised learning strategy
Analyzing an intelligent home communication optimization request by a multidimensional space deep cycle neural network semi-supervised learning strategy;
5) initial result acquisition summary for each depth optimization analysis
Acquiring and summarizing the recommendation results of the intelligent home communication optimization requests;
6) multidimensional space deep circulation neural network optimization strategy semi-supervised learning
Performing semi-supervised learning by combining a tangent expert decision library deep cycle neural network semi-supervised learning method;
7) judging whether the deep optimization analysis evaluation condition is met
Judging according to a deep optimization analysis evaluation condition of a multidimensional space, a cyclic neural network, deep learning, a probability theory, biology, operational research, intelligent optimization and machine learning theory, namely an evaluation function (see formula 1-2), and continuing iteration when the deep optimization analysis evaluation condition is not met;
8) current iteration number plus 1
The current iteration times are increased by 1 time, namely k +1, and k is less than or equal to d;
9) intelligent home communication optimization request analyzed through multidimensional space deep cycle neural network semi-supervised learning strategy
Analyzing an intelligent home communication optimization request by a multidimensional space deep cycle neural network semi-supervised learning strategy;
10) each depth optimization analysis result acquisition summary
Actively reporting and regularly inquiring information of the analysis and optimization result of the intelligent home communication optimization request by a mechanism at preset time intervals;
11) the current iteration times are larger than the maximum iteration times
Judging according to the evaluation condition that the current iteration times are larger than the maximum iteration times, and jumping to 6) to continue iteration when the current iteration times are not satisfied, and ending when the current iteration times are satisfied.
The step 6) of the multidimensional space deep cycle neural network optimization strategy semi-supervised learning and the step 7) of judging whether the deep optimization analysis evaluation conditions are met specifically comprise the following steps:
storing the model:
combined kolmogorov merit functions:
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),λ+β=1 (1-3)
wherein k in formulae (1-2) to (1-6) represents the kth iteration, wherein k must satisfy the condition of k ≦ d, and the condition of k ≦ 1,2, …, d; wherein 1,2 and L are multidimensional space;
in formulae (1-3), (1-4) and (1-5)The method mainly comprises the following steps:andthe information vectors in two aspects are shown as formulas (1-2), (1-3) and (1-4)) (1-5) and (1-6) LmaxG、CmaxG、MmaxG、MmaxK、MminK、 MminGThe current k iteration delay, the current k average delay, the current k flow cost, the current k average flow cost, the maximum value of the historical information delay, the maximum value of the historical information flow cost, the current k information vector, the historical maximum information vector, the current k minimum information vector, the k +1 tangent expert database semi-supervised learning factor, the k +1 reward factor and the historical minimum information vector are deeply optimized, so that the local optimization is picked out by the algorithm.
The intelligent home communication optimized dispatching system has the advantages of low delay, low flow cost, real time and the like, and the advantages of the system can be effectively realized by matching with the method of the system, so that the system has stronger competitiveness.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to these drawings without any creative effort.
Fig. 1 is a flowchart illustrating a deep optimization analysis strategy according to one embodiment of a method for an intelligent home communication optimization scheduling system of the present application;
FIG. 2 is a schematic diagram of a storage model.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the following describes in detail a smart home communication optimized scheduling system and method based on edge calculation, which are provided by the present invention, with reference to the accompanying drawings.
The following provides a detailed description of the embodiments of the present application.
In a first embodiment of the present invention, an intelligent home communication optimization scheduling system based on edge computing is provided, where the system includes:
the intelligent home terminal domain: the intelligent home terminal comprises one or more of a ZigBee intelligent home terminal, a mobile phone terminal and a computer mobile terminal;
an edge access layer: the intelligent home terminal comprises one or more of a ZigBee router, an operator base station and a wireless base station, and realizes the access of an intelligent home terminal domain;
the Internet access layer realizes the access of the operator base station and the wireless base station;
home gateway access layer: the system comprises a plurality of home gateways, a ZigBee router and an Internet;
core layer: the intelligent household terminal comprises at least one optimized scheduler, and optimized scheduling requests from a ZigBee intelligent household terminal, a mobile phone terminal and a computer mobile terminal are realized;
the intelligent household communication optimization function analyzer: the intelligent home communication optimization service system comprises an edge computing intelligent home communication optimization service core cloud, and realizes core processing of optimized scheduling information from a ZigBee intelligent home terminal, a mobile phone terminal and a computer mobile terminal, wherein an intelligent home communication optimization function analyzer mainly completes analysis processing of an intelligent home communication optimization request, forwards related information after the analysis processing to a corresponding analysis result, and also comprises services of processing the rest of computing, storing, networking and the like except for migrating to the ZigBee intelligent home terminal.
In a second embodiment of the invention, the ZigBee smart home terminal accesses to the ZigBee router through a ZigBee network; the mobile phone mobile terminal and the computer mobile terminal are respectively accessed to an operator base station and a wireless base station through an operator network and a wireless network; the operator base station and the wireless base station are accessed to the internet access layer and then accessed to the home gateway access layer; the ZigBee router is accessed to a home gateway access layer; the home gateway is accessed to an optimization scheduler of a core layer; and the optimization scheduler is accessed to an edge computing intelligent home communication optimization service core cloud of the intelligent home communication optimization function analyzer.
In a third embodiment of the present invention, the present invention provides an intelligent home communication optimization scheduling method based on edge calculation, including the following steps:
1) the intelligent home terminal domain sends out a ZigBee intelligent home terminal communication optimization request;
2) the ZigBee intelligent home terminal communication optimization request is transmitted to a marginal computing intelligent home communication optimization service core cloud in a marginal intelligent home communication optimization function analyzer; the edge computing intelligent home communication optimization service core cloud processes a ZigBee intelligent home terminal communication optimization request; feeding back the processed ZigBee intelligent home terminal communication optimization request result to an optimization scheduler of a core layer;
3) the optimization scheduler returns the processed communication optimization request result of the ZigBee intelligent home terminal to a home gateway of a home gateway access layer;
4) the home gateway returns the processed ZigBee intelligent home terminal communication optimization request result to a ZigBee router of an edge access layer or returns the processed ZigBee intelligent home terminal communication optimization request result to the operator base station and the wireless base station through an Internet layer; and the ZigBee router or the operator base station and the wireless base station return the processed ZigBee intelligent home terminal communication optimization request result to the ZigBee intelligent home terminal and implement the optimized ZigBee intelligent home terminal communication optimization request.
In a fourth embodiment of the present invention, in step 1), the smart home terminal domain sends out a communication optimization request to the ZigBee smart home terminal and processes a communication optimization request of the ZigBee smart home terminal after part of the calculation, storage and network migration to the terminal, or a communication optimization request of the ZigBee smart home terminal sent by a mobile phone terminal or a mobile computer terminal.
In a fifth embodiment of the present invention, the processed communication optimization request result of the ZigBee smart home terminal includes a processed communication optimization request of the ZigBee smart home terminal and a remaining task request result except for a part of communication optimization tasks such as calculation, storage, and network migrated to the terminal.
In a sixth embodiment of the present invention, the processing, by the smart home communication optimization function analyzer, the ZigBee smart home terminal communication optimization request includes: the method comprises the steps of receiving a ZigBee intelligent home communication optimization request, analyzing the intelligent home communication optimization request by a multi-dimensional space deep circulation neural network strategy, outputting a recommendation result and semi-supervised learning of the multi-dimensional space deep circulation neural network strategy. Wherein, each intelligent home communication optimization request information mainly comprises: delay L, flow cost C. The time delay L and the flow cost C of each intelligent home communication optimization request are deeply optimized by analyzing the intelligent home communication optimization request, and the multi-dimensional space deep circulation neural network strategy semi-supervised learning is realized and a recommendation result is given.
As shown in fig. 1, in a seventh embodiment of the present invention, the specific steps of processing the ZigBee smart home terminal communication optimization request by the smart home communication optimization function analyzer are as follows:
1) ZigBee intelligent home communication optimization request receiving, acquiring and summarizing
Actively reporting every preset time and regularly inquiring to obtain an intelligent home communication optimization request by a mechanism, and summarizing the information;
2) setting iteration initial parameters
Setting the iteration maximum algebra d as 50;
3) current iteration number k plus 1
The current iteration times are increased by 1 time, namely k +1, and k is less than or equal to d;
4) intelligent home communication optimization request analyzed through multidimensional space deep cycle neural network semi-supervised learning strategy
Analyzing an intelligent home communication optimization request by a multidimensional space deep cycle neural network semi-supervised learning strategy;
5) initial result acquisition summary for each depth optimization analysis
Acquiring and summarizing the recommendation results of the intelligent home communication optimization requests;
6) multidimensional space deep circulation neural network optimization strategy semi-supervised learning
Performing semi-supervised learning by combining a tangent expert decision library deep cycle neural network semi-supervised learning method;
7) judging whether the deep optimization analysis evaluation condition is met
Judging according to a deep optimization analysis evaluation condition of a multidimensional space, a cyclic neural network, deep learning, a probability theory, biology, operational research, intelligent optimization and machine learning theory, namely an evaluation function (see formula 1-2), and continuing iteration when the deep optimization analysis evaluation condition is not met;
8) current iteration number plus 1
The current iteration times are increased by 1 time, namely k +1, and k is less than or equal to d;
9) intelligent home communication optimization request analyzed through multidimensional space deep cycle neural network semi-supervised learning strategy
Analyzing an intelligent home communication optimization request by a multidimensional space deep cycle neural network semi-supervised learning strategy;
10) each depth optimization analysis result acquisition summary
Actively reporting and regularly inquiring information of the analysis and optimization result of the intelligent home communication optimization request by a mechanism at preset time intervals;
11) the current iteration times are larger than the maximum iteration times
Judging according to the evaluation condition that the current iteration times are larger than the maximum iteration times, and jumping to 6) to continue iteration when the current iteration times are not satisfied, and ending when the current iteration times are satisfied.
The deep optimization idea is to judge and analyze the information of each intelligent home communication optimization request, and each intelligent home communication optimization request has different priority levels. The intelligent home communication optimization method analyzes the intelligent home communication optimization request by a depth optimization strategy with an optimal depth optimization analysis evaluation function. The method is combined with a tangent expert decision library deep cycle neural network semi-supervised learning method to realize the advantages of low delay, low flow cost, real time and the like. The algorithm adopts real-time active and passive collection of intelligent home communication optimization request information and real-time analysis, and obviously optimizes the time delay L, flow cost C and other indexes of each intelligent home communication optimization request result.
In an eighth embodiment of the present invention, the step 6) of semi-supervised learning of the multidimensional space deep recurrent neural network optimization strategy and the step 7) of judging whether the deep optimization analysis evaluation condition is satisfied specifically include:
storage model (as shown in fig. 2):
combined kolmogorov merit functions:
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),λ+β=1 (1-3)
wherein k in formulae (1-2) to (1-6) represents the kth iteration, wherein k must satisfy the condition of k ≦ d, and the condition of k ≦ 1,2, …, d; wherein 1,2 and L are multidimensional space;
in formulae (1-3), (1-4) and (1-5)The method mainly comprises the following steps:andtwo-dimensional information vector, in the formulae (1-2), (1-3), (1-4), (1-5) and (1-6) LmaxG、CmaxG、MmaxG、MmaxK、MminK、 MminGRespectively carrying out depth optimization on the current k iteration delay, the current k average delay, the current k flow cost, the current k average flow cost, the maximum value of historical information delay, the maximum value of historical information flow cost, the current k information vector, the historical maximum information vector, the current k minimum information vector, the k +1 tangent expert database semi-supervised learning factor, the k +1 reward factor, the historical maximum information vectorAnd small information vectors enable the algorithm to pick out local optima.
The intelligent home communication optimized dispatching system has the advantages of low delay, low flow cost, real time and the like, and the advantages of the system can be effectively realized by matching with the method of the system, so that the system has stronger competitiveness.
The same and similar parts in the various embodiments in this specification may be referred to each other. The above-described embodiments of the present invention should not be construed as limiting the scope of the present invention.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (7)
1. An intelligent home communication optimal scheduling system based on edge computing comprises:
the intelligent home terminal domain: the intelligent home terminal comprises one or more of a ZigBee intelligent home terminal, a mobile phone terminal and a computer mobile terminal; the intelligent home terminal domain sends out a ZigBee intelligent home terminal communication optimization request;
an edge access layer: the intelligent home terminal comprises one or more of a ZigBee router, an operator base station and a wireless base station, and realizes the access of an intelligent home terminal domain;
the Internet access layer realizes the access of the operator base station and the wireless base station;
home gateway access layer: the system comprises a plurality of home gateways, a ZigBee router and the Internet;
core layer: the intelligent household terminal comprises at least one optimized scheduler, and optimized scheduling requests from a ZigBee intelligent household terminal, a mobile phone terminal and a computer mobile terminal are realized;
the intelligent household communication optimization function analyzer: the method comprises the steps that an edge computing intelligent home communication optimization service core cloud is used for realizing core processing of optimized scheduling information from a ZigBee intelligent home terminal, a mobile phone terminal and a computer mobile terminal; the ZigBee intelligent home terminal communication optimization request is transmitted to a marginal computing intelligent home communication optimization service core cloud in the intelligent home communication optimization function analyzer; the intelligent home communication optimization service core cloud of edge computing handles zigBee intelligent home terminal communication optimization request, intelligent home communication optimization function analyzer is used for specifically:
1) ZigBee intelligent home communication optimization request receiving, acquiring and summarizing
Actively reporting every preset time and regularly inquiring to obtain an intelligent home communication optimization request by a mechanism, and summarizing the information;
2) setting iteration initial parameters
Setting the iteration maximum algebra d as 50;
3) current iteration number k plus 1
The current iteration times are increased by 1 time, namely k +1, and k is less than or equal to d;
4) intelligent home communication optimization request analyzed through multidimensional space deep cycle neural network semi-supervised learning strategy
Analyzing an intelligent home communication optimization request by a multidimensional space deep cycle neural network semi-supervised learning strategy;
5) initial result acquisition summary for each depth optimization analysis
Acquiring and summarizing the recommendation results of the intelligent home communication optimization requests;
6) multidimensional space deep circulation neural network optimization strategy semi-supervised learning
Performing semi-supervised learning by combining a tangent expert decision library deep cycle neural network semi-supervised learning method;
7) judging whether the deep optimization analysis evaluation condition is met
Judging according to a deep optimization analysis evaluation condition, namely an evaluation function, of a multidimensional space, a cyclic neural network, deep learning, a probability theory, biology, operational research, intelligent optimization and a machine learning theory, and continuing iteration when the deep optimization analysis evaluation condition is not met;
8) current iteration number plus 1
The current iteration times are increased by 1 time, namely k +1, and k is less than or equal to d;
9) intelligent home communication optimization request analyzed through multidimensional space deep cycle neural network semi-supervised learning strategy
Analyzing an intelligent home communication optimization request by a multidimensional space deep cycle neural network semi-supervised learning strategy;
10) each depth optimization analysis result acquisition summary
Actively reporting and regularly inquiring information of the analysis and optimization result of the intelligent home communication optimization request by a mechanism at preset time intervals;
11) the current iteration times are larger than the maximum iteration times
Judging according to the evaluation condition that the current iteration times are larger than the maximum iteration times, and jumping to 6) to continue iteration when the current iteration times are not satisfied, and ending when the current iteration times are satisfied.
2. The system of claim 1, wherein: the ZigBee intelligent home terminal is accessed to the ZigBee router through a ZigBee network; the mobile phone mobile terminal and the computer mobile terminal are respectively accessed to an operator base station and a wireless base station through an operator network and a wireless network; the operator base station and the wireless base station are accessed to the home gateway access layer after being accessed to the Internet access layer; the ZigBee router is accessed to a home gateway access layer; the home gateway is accessed to an optimization scheduler of a core layer; the optimization scheduler is accessed to an edge computing intelligent home communication optimization service core cloud of the intelligent home communication optimization function analyzer.
3. An intelligent home communication optimal scheduling method based on edge calculation is characterized by comprising the following steps:
1) the intelligent home terminal domain sends out a ZigBee intelligent home terminal communication optimization request;
2) the ZigBee intelligent home terminal communication optimization request is transmitted to a marginal computing intelligent home communication optimization service core cloud in the intelligent home communication optimization function analyzer; the edge computing intelligent home communication optimization service core cloud processes a ZigBee intelligent home terminal communication optimization request; feeding back the processed ZigBee intelligent home terminal communication optimization request result to an optimization scheduler of the core layer;
3) the optimization scheduler returns the processed communication optimization request result of the ZigBee intelligent home terminal to a home gateway of a home gateway access layer;
4) the home gateway returns the processed ZigBee intelligent home terminal communication optimization request result to a ZigBee router of an edge access layer or returns the processed ZigBee intelligent home terminal communication optimization request result to an operator base station and a wireless base station through an Internet layer; the ZigBee router or the operator base station and the wireless base station return the processed ZigBee intelligent home terminal communication optimization request result to the ZigBee intelligent home terminal and implement the optimized ZigBee intelligent home terminal communication optimization request;
the intelligent home communication optimization function analyzer is used for processing a ZigBee intelligent home terminal communication optimization request and comprises the following specific steps:
1) ZigBee intelligent home communication optimization request receiving, acquiring and summarizing
Actively reporting every preset time and regularly inquiring to obtain an intelligent home communication optimization request by a mechanism, and summarizing the information;
2) setting iteration initial parameters
Setting the iteration maximum algebra d as 50;
3) current iteration number k plus 1
The current iteration times are increased by 1 time, namely k +1, and k is less than or equal to d;
4) intelligent home communication optimization request analyzed through multidimensional space deep cycle neural network semi-supervised learning strategy
Analyzing an intelligent home communication optimization request by a multidimensional space deep cycle neural network semi-supervised learning strategy;
5) initial result acquisition summary for each depth optimization analysis
Acquiring and summarizing the recommendation results of the intelligent home communication optimization requests;
6) multidimensional space deep circulation neural network optimization strategy semi-supervised learning
Performing semi-supervised learning by combining a tangent expert decision library deep cycle neural network semi-supervised learning method;
7) judging whether the deep optimization analysis evaluation condition is met
Judging according to a deep optimization analysis evaluation condition, namely an evaluation function, of a multidimensional space, a cyclic neural network, deep learning, a probability theory, biology, operational research, intelligent optimization and a machine learning theory, and continuing iteration when the deep optimization analysis evaluation condition is not met;
8) current iteration number plus 1
The current iteration times are increased by 1 time, namely k +1, and k is less than or equal to d;
9) intelligent home communication optimization request analyzed through multidimensional space deep cycle neural network semi-supervised learning strategy
Analyzing an intelligent home communication optimization request by a multidimensional space deep cycle neural network semi-supervised learning strategy;
10) each depth optimization analysis result acquisition summary
Actively reporting and regularly inquiring information of the analysis and optimization result of the intelligent home communication optimization request by a mechanism at preset time intervals;
11) the current iteration times are larger than the maximum iteration times
Judging according to the evaluation condition that the current iteration times are larger than the maximum iteration times, and jumping to 6) to continue iteration when the current iteration times are not satisfied, and ending when the current iteration times are satisfied.
4. The method according to claim 3, wherein the intelligent home terminal domain in step 1) sends a communication optimization request to the ZigBee intelligent home terminal and processes a communication optimization request of the ZigBee intelligent home terminal after part of calculation, storage and network migration to the terminal, or a communication optimization request of the ZigBee intelligent home terminal sent by a mobile phone terminal or a computer mobile terminal.
5. The method according to claim 3, wherein the processed ZigBee intelligent home terminal communication optimization request result comprises a processed ZigBee intelligent home terminal communication optimization request and a residual task request result except for partial communication optimization tasks of calculation, storage, network and the like transferred to the terminal.
6. The method according to claim 3, wherein the smart home communication optimization function analyzer processing the ZigBee smart home terminal communication optimization request comprises: the method comprises the steps of receiving a ZigBee intelligent home communication optimization request, analyzing the intelligent home communication optimization request by a multidimensional space deep circulation neural network strategy, outputting a recommendation result and performing semi-supervised learning of the multidimensional space deep circulation neural network strategy.
7. The method according to claim 3, wherein the step 6) of semi-supervised learning of the multidimensional space deep cycle neural network optimization strategy and the step 7) of judging whether the deep optimization analysis evaluation condition is satisfied specifically comprise:
storing the model:
combined kolmogorov merit functions:
deep cycle neural network optimization function:
wherein k in formulae (1-1) to (1-6) represents the kth iteration, wherein k must satisfy the condition that k is not more than d, and the condition that k is 1,2, L, d is satisfied; wherein 1,2 and L are multidimensional space;
m in the formulae (1-3), (1-4) and (1-5)ijt kThe method mainly comprises the following steps:andtwo-dimensional information vector, in the formulae (1-2), (1-3), (1-4), (1-5) and (1-6) LmaxG、CmaxG、MmaxG、MmaxK、MminK、 MminGRespectively carrying out depth optimization on the current k iteration delay, the current k average delay, the current k flow cost, the current k average flow cost, the maximum value of historical information delay, the maximum value of historical information flow cost, the current k information vector and the historical maximum informationThe information vector, the current k-th maximum information vector, the current k-th minimum information vector, the k + 1-th tangent expert database semi-supervised learning factor, the k + 1-th reward factor and the historical minimum information vector are selected, so that the local optimum is selected by the algorithm.
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 CN108833227A (en) | 2018-11-16 |
CN108833227B true 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) |
Families Citing this family (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 |
CN112040189B (en) * | 2020-09-01 | 2022-06-24 | 浙江大华技术股份有限公司 | Monitoring method and system of front-end equipment and storage medium |
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 |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN108833227A (en) | 2018-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108833227B (en) | Intelligent home communication optimal scheduling system and method based on edge calculation | |
Yu et al. | Toward resource-efficient federated learning in mobile edge computing | |
Liu et al. | Big-data-based intelligent spectrum sensing for heterogeneous spectrum communications in 5G | |
CN108924198B (en) | Data scheduling method, device and system based on edge calculation | |
Wan et al. | Task-driven resource assignment in mobile edge computing exploiting evolutionary computation | |
CN110324170B (en) | Data analysis equipment, multi-model co-decision system and method | |
CN110968426B (en) | Edge cloud collaborative k-means clustering model optimization method based on online learning | |
CN113435472A (en) | Vehicle-mounted computing power network user demand prediction method, system, device and medium | |
CN108023840B (en) | OVS network flow acceleration optimization method and OVS network flow acceleration optimization system | |
Bayrakdar et al. | Artificial bee colony–based spectrum handoff algorithm in wireless cognitive radio networks | |
Hu et al. | Edge intelligence for real-time data analytics in an IoT-based smart metering system | |
Dai et al. | A learning algorithm for real-time service in vehicular networks with mobile-edge computing | |
Akhtar et al. | A novel hybrid meta‐heuristic concept for green communication in IoT networks: An intelligent clustering model | |
Ren et al. | An energy‐aware method for task allocation in the Internet of things using a hybrid optimization algorithm | |
Rui et al. | CLPM: A cooperative link prediction model for industrial Internet of Things using partitioned stacked denoising autoencoder | |
Ma et al. | A deep reinforcement learning approach for dynamic contents caching in HetNets | |
CN108829846B (en) | Service recommendation platform data clustering optimization system and method based on user characteristics | |
US20220172054A1 (en) | Intermediate network node and method performed therein for handling data of communication networks | |
CN108833550B (en) | Method and device for sensing agricultural optimized scheduling | |
Liu et al. | Multiple Local‐Edge‐Cloud Collaboration Strategies in Industrial Internet of Things: A Hybrid Genetic‐Based Approach | |
CN108848514B (en) | Data communication optimization method and data communication optimizer | |
CN112437460A (en) | IP address black and gray list analysis method, server, terminal and storage medium | |
Torki et al. | Optimization Resource Allocation in NOMA-based Fog Computing with a Hybrid Algorithm | |
CN117279019B (en) | Method and device for predicting spectrum efficiency, electronic equipment and storage medium | |
CN109982295A (en) | The method for pushing of service template and the pusher of service template |
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 |