CN110138604A - A kind of Internet of things hardware platform automatic generation method towards multi-performance index - Google Patents
A kind of Internet of things hardware platform automatic generation method towards multi-performance index Download PDFInfo
- Publication number
- CN110138604A CN110138604A CN201910356053.XA CN201910356053A CN110138604A CN 110138604 A CN110138604 A CN 110138604A CN 201910356053 A CN201910356053 A CN 201910356053A CN 110138604 A CN110138604 A CN 110138604A
- Authority
- CN
- China
- Prior art keywords
- hardware
- internet
- things
- hardware platform
- user
- 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
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
- H04L41/5051—Service on demand, e.g. definition and deployment of services in real time
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of Internet of things hardware platform automatic generation method towards multi-performance index, it include: the foundation in (1) hardware performance data library, hardware performance data library includes following four part: hardware energy consumption data library, hardware process speed database, API Calls speed data library, hardware interface and Pricedata；(2) analysis of user demand file and user written program logic；(3) Internet of things hardware platform dynamic constrained condition, including two indices: application execution time and average energy consumption are generated；(4) Internet of things hardware platform static constraint condition, including two indices: hardware platform scalability and price are generated；(5) optimization problem is solved, the optimization aim of the static state being converted in step (3) and step (4), dynamic constrained condition and user's statement is inputted, is configured using the solver of mixed integer nonlinear programming problem by optimal Internet of things hardware is solved.
Description
Technical field
The present invention relates to the prediction of the Key Performance Indicator of Internet of things hardware platform (such as energy consumption, real-time), with according to
Demand of the family to node Key Performance Indicator automatically generates hardware module method connected to it in Internet of things hardware platform.
Background technique
In recent years, with the development of the technologies such as micro-electromechanical technology (MEMS), novel sensor goes out with microcomputer layer
Not poor, the Internet of Things application based on these hardware also achieves rapid growth.According to statistics, global internet of things equipment in 2017
Quantity has just reached 8,400,000,000, and 6,400,000,000 than 2016 increase 31%, has for the first time been more than population in the world (7,500,000,000).According to conservative pre-
It surveys, active internet of things equipment was up to 21,500,000,000 in 2025 in global range.
However, being answered relative to traditional personal computer (Personal Computer, PC)/cluster server software
The development process still efficiency of exploitation, Internet of Things application is lower.This is because the hardware structure of PC and server has become
In unified (such as central processing unit uses von Neumann framework), application developer need to only be concerned about software development work on it
Make.However Internet of Things is using the exploitation of the type selecting comprising hardware platform module and corresponding application.In general, Internet of things hardware is flat
Platform is a custom-made comprising miniature processing unit (Micro-Control Unit, MCU), communication module and other sensings
The embedded system of device, Internet of Things software application needs are customized according to different hardware platforms.Internet of things hardware platform one
As be divided into three parts: mainboard, scuta and peripheral hardware.Mainboard mainly includes the main computing component (such as MCU, memory) of system,
Scuta is inserted into the extension element on mainboard, and general action is to provide more interfaces, and peripheral hardware is connected directly to mainboard or passes through
Scuta is indirectly coupled on mainboard to provide the functions such as sensing, control.Therefore up to the present, due to Internet of things hardware and software
It is strong coupling, still none general internet of things equipment platform is occupied an leading position in the market.
Just due to this, for the layman of Internet of Things or embedded system field, creation one meets oneself demand
Internet of Things application be it is very difficult, reason has two: (1) Internet of things hardware platform and its component it is many kinds of and mutually it is different
Structure, layman is difficult to search out most suitable hardware in type selecting space big in this way.(2) hardware developers are for exploitation
Hardware platform and its software out has different requirement.The low power capabilities such as applied under some scenes are extremely seen
Weight, and the price of hardware device entirety can be the index being prioritized under other scene.This species diversity is to Internet of Things
The building of net hardware platform provides a variety of possibilities, but also brings great complexity: needing to meet between hardware component
A variety of requirements such as complicated interface, voltage.
Just because of the two above exploitation difficult points, although internet of things equipment quantity is caused to quickly increase, Internet of Things application
The daily life of the mankind is not infiltrated through as PC or server application, Internet of Things application and development efficiency is lowly to keep object in check
One big bottleneck of networking development.The select permeability of hardware needs to consider several points:
(1) suitability of user performance demand: the Key Performance Indicators such as price, energy consumption, scalability of generated hardware
Need to meet the requirement of user.
(2) suitability of software: the hardware of selection is required to function (such as WiFi connection, temperature for supporting developer to need
Degree perception, driving relay etc.)
(3) suitability of hardware: such as supply voltage, physical interface quantity and type
The performance requirement of user can be divided into two classes: dynamic indicator and Static State Index.So-called Static State Index refers to that program is patrolled
Collect incoherent attribute (such as price)；And dynamic indicator is then closely related (such as power consumption) with programmed logic.
Summary of the invention
The present invention will overcome the disadvantages mentioned above of the prior art, carry out analysis to user demand and to Internet of Things by automation
The prediction of net hardware platform Key Performance Indicator automatically generates the side of optimal Internet of things hardware platform by solving optimization problem
Method.
In order to achieve the above object, the technical solution used in the present invention is: a kind of Internet of Things towards multi-performance index is hard
Part platform automatic generation method, comprising the following steps:
(1) foundation in hardware performance data library, hardware performance data library include following four part: hardware energy consumption data
Library, hardware process speed database, API Calls speed data library, hardware interface and Pricedata.
(2) analysis of user demand file and user written program logic, comprising:
2.1) it is every to obtain the Internet of things hardware platform that user is used to state that it to wish to generate for the analysis of user demand file
The demand file of performance indicator obtains the mathematic(al) representation of user demand by analysis.
2.2) analysis for the programmed logic that user writes generates the controlling stream graph of code using the method for code static analysis
With the weight of each control flow branching.
(3) Internet of things hardware platform dynamic constrained condition, including two indices: application execution time and average energy are generated
Consumption, the specific steps are as follows:
3.1) generation of application execution time dynamic constrained condition, according to application execution time prediction model and user demand
It generates constraint condition nonlinear inequalities (or optimization aim).
3.2) generation for applying average power consumption dynamic constrained condition, according to using average power consumption prediction model and user demand
It generates constraint condition nonlinear inequalities (or optimization aim).
(4) Internet of things hardware platform static constraint condition, including two indices: hardware platform scalability and valence are generated
Lattice, the specific steps are as follows:
4.1) generation for applying scalability static constraint condition, generates according to scalability computation model and user demand
Inequality (or optimization aim) of constraint condition.
4.2) generation for applying total price static constraint condition, generates according to using total price computation model and user demand
Inequality (or optimization aim) of constraint condition.
(5) optimization problem is solved, by the static state being converted in step 3) and step 4), dynamic constrained condition and user
The optimization aim of statement inputs, and will solve optimal Internet of things hardware using the solver of mixed integer nonlinear programming problem
Configuration.
The invention has the advantages that compared with prior art, the present invention is when automatically generating internet of things equipment platform, except consideration
Outside the integrality that the consistency of electrical characteristic and hardware platform support user logic between internet of things equipment, by developer
Obtain various important performance indexes (such as power consumption, scalability, execution time and the total price of more difficult Internet of things hardware platform
Lattice) modeling and constraint condition or optimization aim as hardware platform generation are carried out, developer is best suitable for Internet of Things to generate
The hardware platform of application demand has greatly accelerated the Internet of Things development process of developer to reduce developer's trial and error cost.
Detailed description of the invention
Fig. 1 is internet of things equipment platform product process figure of the invention.
Fig. 2 is the application control flow graph that program flow analysis of the invention generates and the hardware configuration ultimately generated.
Specific embodiment
The present invention analyzes user demand and by what is automated to Internet of things hardware platform Key Performance Indicator
Prediction, the method for optimal Internet of things hardware platform is automatically generated by solving optimization problem.In order to achieve the above object, of the invention
It is adopted the technical scheme that: a kind of Internet of things hardware platform automatic generation method towards multi-performance index, including following step
It is rapid:
(1) foundation in hardware performance data library, hardware performance data library include following components: hardware energy consumption data
Library, hardware process speed database, API Calls speed data library, hardware interface and Pricedata, the specific steps are as follows:
(1.1) foundation in hardware energy consumption data library, energy consumption Energy in use logger Monsoon Power Monitor are surveyed
Trying program is API primary every 1s operation, other times suspend mode.Pass through the periodical energy consumption data of record energy consumption logger output
Come energy consumption when obtaining API operation.APIf is recorded in the energy consumption for corresponding to energy consumption grade k on component i and mainboard j and corresponding calling
It is long, it is denoted as respectivelyWith
(1.2) foundation of hardware process speed database.It is corresponding for the syntax rule u on the platform i of programming language
MCU amount of cycles y needed for assembly codei,u, according to the databook of platform, by formula ti,u=yi,u/νiηiObtain grammer
The corresponding hardware process speed t of regular ui,u。
(1.3) foundation in API Calls speed data library.Classify first to each hardware platform according to its architecture
(such as ARM Cortex, AVR ATMega, TI MSP series), and to the representative hardware and Application Programming Interface in every one kind
(Application Programming Interface, API) does api class and does not measure, and single API Calls time is inserted using code
The mode of stake, is inserted into timestamp before and after API execution, and the difference of two timestamps is that API is corresponding to holding on hardware platform thus
The row time；On the basis of basic database, the automation carried out laterally, longitudinal extends offline, to automatically complete pair
The complete measurement of hardware platform and API.
(1.3.1) is extending transversely to be referred to according to quantization performance index (such as core between same category Different Individual platform
Clock frequency, instruction set throughput etc.) it is modeled, extend the database of all individual platforms under raw cost categories.The tune of API
Related with instruction set throughput with the core clock frequencies of time and hardware platform, corresponding formula is ti,f=ti′,fvi′ηi′/vi
ηi.Wherein ti,f/ti′,f、vi/vi′And ηi/ηi′The respectively allocating time of the APIf of platform i and i ', platform core clock frequencies
With instruction set throughput.
(1.3.2) Longitudinal Extension refers to the resource occupation index quantified between measurement result and API according to basic API (such as
Code counting, system function call number etc.) ratio calculated, extension generates all API's on the same hardware platform
Database.
(1.4) foundation of hardware interface and Pricedata, this database contain hardware interface quantity and type, and hard
The information of the part market price, these information can be obtained from the databook of production firm.
(2) analysis of user demand file and user written program logic.
(2.1) it is each to obtain the Internet of things hardware platform that user is used to state that it wishes to generate for the analysis of user demand file
The demand file of item performance indicator is led to wherein containing the constraint condition of optimization aim and performance indexes desired by user
It crosses analysis and obtains the mathematic(al) representation of user demand.If user demand is " to minimize energy consumption, and overall price is lower than 100 people
Coin ", then generating mathematic(al) representation isWhereinWithRespectively represent the energy consumption and valence for generating hardware platform
Lattice
(2.2) analysis for the programmed logic that user writes, using the code Static Analysis Method based on Valgrind to obtain
To program control flowchart, stain analysis (taint analysis) is carried out to journey to the key variables in branch point and circulation point
Sequence logic is inversely recalled, with locator variable source.Due to the particularity of Internet of Things application, if variable-value is related with external environment
(such as a certain condition is that outer moisture > 90% takes very) introduces user to the prediction of environment as input herein, ultimately generates generation
The weight of the controlling stream graph of code and each control flow branching.
(3) Internet of things hardware platform dynamic constrained condition, including two indices: application execution time and average energy are generated
Consumption, the specific steps are as follows:
(3.1) generation of application execution time dynamic constrained condition, foundation and generation constraint condition including prediction model
Two parts:
The foundation of (3.1.1) code execution time dynamic indicator prediction model.This patent indicates a spy using vector d
Fixed Internet of things hardware platform, WithRepresent data
All mainboards, scuta and peripheral hardware in library, binary select variable diRepresenting whether hardware i is selected, possible value is 1 or 0,
Such as di=1 expression hardware i is included in the hardware platform ultimately generated.Variable d and this definition in step 4) and step 5)
It is identical.
For a specific Internet of things hardware platform d and user application U, internet of things equipment runs the time of codeIt can be represented as calling Application Programming Interface (Application Programming Interface, API)
Time tAPI(d), the runing time t of non-API codel(d) with dormancy time tidleThe sum of (U), it is as follows:
It can specifically further indicate that are as follows:
Wherein binary selects variable diAnd djIt represents hardware or whether is selected, possible value is 1 or 0, such as di=1
Indicate that hardware i is included in the hardware platform ultimately generated；F and l represents all API obtained from personal code work and entirety is non-
The set of API code,WithThe all scutas and peripheral hardware of offer APIf in database are provided,It represents in database
Entirety, βfWith βuThe operation for representing the APAnd if non-API code u of passage path weighting counts；ti,j,fAPIf in mainboard i and
Runing time on peripheral hardware j, ti,uIt is runing time of the non-API code on mainboard i；Φ (U) is extracted from personal code work U
The operation of dormancy time；
The generation of (3.1.2) constraint condition.Based on step 1.2) and runing time database 1.3), and in step 2.2)
The personal code work routing information of acquisition can get the fortune of this personal code work using the formula (1) in step 3.1.1) with formula (2)
In conjunction with user's constraint information (or optimization aim) of step 2.1) quadratic inequality can be obtained, i.e., in row time calculation formula
The constraint condition (or optimization aim) of time is executed for code.
(3.2) generation for applying average power consumption dynamic constrained condition, foundation and generation constraint condition including prediction model
Two parts:
(3.2.1) applies the foundation of average power consumption dynamic indicator prediction model.The average function of one Internet of things hardware platform
Consumption is represented by average power consumption of each component in a code loop.Because different mainboards possesses different electrical spies
Property, even the same peripheral hardware and scuta, different power consumption numbers can also be possessed by being inserted on different mainboards.Therefore it is specific for one
Internet of things hardware platform d and user application U, internet of things equipment run code average power consumptionIt may be expressed as:
Wherein binary selects variable diAnd djIt represents hardware or whether is selected, possible value is 1 or 0, such as di=1
Indicate that hardware i is included in the hardware platform ultimately generated, Pi(U) and Pi,j(U) hardware i or hard when representing operation code U
The average power consumption of part i, j, specifically may be expressed as:
It is the energy consumption grade of component i, usesWithRespectively indicate idle energy consumption and activity energy consumption etc.
The set of grade, then have (or) with(or) be component i (or
Component i is on mainboard j) in the duty ratio and power consumption values of energy consumption grade k；Duty ratio is the ratio of active time and total time, i.e.,WithWhereinWhen being that component i is in energy consumption grade k
Between,It is the set for the API that component i is provided,It is that i will be made to enter k-th in the APIf of mainboard j invocation component i
The time span of energy consumption grade, βfThe operation for representing the APIf of passage path weighting counts,One that runs code is indicated to follow
It time required for ring, is obtained from step 3.1).
The generation of (3.2.2) constraint condition.Hardware energy consumption data library based on step 1.1), with acquisition in step 2.2)
Personal code work routing information can get the average energy consumption of this personal code work using the formula (3) in step 3.2.1) with formula (4)
A quadratic inequality can be obtained in conjunction with user's constraint information (or optimization aim) of step 2.1) in calculation formula, as average
The constraint condition (or optimization aim) of energy consumption.
(4) Internet of things hardware platform static constraint condition, including two indices: hardware platform scalability and valence are generated
Lattice, the specific steps are as follows:
(4.1) generation of Internet of things hardware platform extensibility Index Constraints condition.In this patent, it is hard to define Internet of Things
The scalability of part platform is the quantity of the still remaining physical interface of mainboard after the completion of user connects using required hardware.It can
With with by calculate connection after the completion of remaining physical interface quantityWith remaining MCU pin quantityCommon table
Show, specific Internet of things hardware platform d'sWithIt may be expressed as:
Wherein binary selects variable diIt represents hardware or whether is selected, possible value is 1 or 0, such as di=1 indicates
Hardware i is included in the hardware platform ultimately generated；WithRepresent all mainboards, scuta and the peripheral hardware in database；WithThe set of physical interface type and interface communication type is respectively represented, i.e., Each Port
Two Pin are occupied,AndWithIt is three
Tuple<i, W, I>offer/consumption physical interface quantity,WithIt is triple<i, W, I>provide/disappear
The MCU pin quantity of consumption.
Demand of the user to Mr. Yu's type scalability can connect according to hardware in formula (5) and formula (6) and step 1.4)
Mouth quantity database is expressed using mathematic(al) representation, in conjunction with the user demand of step 2.1), and then is converted into about hardware
The inequality of platform selecting.Since remaining number of pin is that the quantity of remaining physical interface and MCU pin quantity codetermine
, therefore demand of the user to certain interface will be converted into a physical interface number constraint and MCU pin constraint.Such as user
Demand is that " Pin of remaining I2C type is more than 6 " will be converted into
(4.2) generation of Internet of things hardware Platform Price constraint condition.Such as a specific Internet of things hardware platform di's
Price may be expressed as:
WhereinIndicate the price of a specific Internet of things hardware platform d, ciIt is the price of component i, binary selection
Variable diIt represents hardware or whether is selected, possible value is 1 or 0, such as di=1 expression hardware i, which is included in, to be ultimately generated
In hardware platform,WithRepresent all mainboards, scuta and the peripheral hardware in database.
User can be according to the hardware price in formula (7) and step 1.4) for the constraint condition (or optimization aim) of price
Database is expressed using mathematic(al) representation, in conjunction with the user demand of step 21), that is, produces one about diDiffer
Formula, the as mathematic(al) representation of price constraints condition.
(5) optimization problem is solved, by the static state being converted in step 3) and step 4), dynamic constrained condition and user
The optimization aim of statement inputs, and since dynamic constrained condition is the non-linear MIXED INTEGER inequality about d, therefore solver needs
Use Nonlinear Mixed Integer Programming Problem solver.Solver configures d for optimal Internet of things hardware is solved.
Content described in this specification embodiment is only enumerating to the way of realization of inventive concept, protection of the invention
Range should not be construed as being limited to the specific forms stated in the embodiments, and protection scope of the present invention is also and in art technology
Personnel conceive according to the present invention it is conceivable that equivalent technologies mean.
Claims (1)
1. a kind of Internet of things hardware platform automatic generation method towards multi-performance index, comprising the following steps:
(1) foundation in hardware performance data library, hardware performance data library include following four part: hardware energy consumption data library, firmly
Part processing speed database, API Calls speed data library, hardware interface and Pricedata；
(2) analysis of user demand file and user written program logic, comprising:
2.1) analysis of user demand file obtains user and is used to state the Internet of things hardware platform properties that it wishes to generate
The demand file of index obtains the mathematic(al) representation of user demand by analysis；
2.2) analysis for the programmed logic that user writes generates the controlling stream graph of code and every using the method for code static analysis
The weight of one control flow branching；
(3) Internet of things hardware platform dynamic constrained condition, including two indices: application execution time and average energy consumption, tool are generated
Steps are as follows for body:
3.1) generation of application execution time dynamic constrained condition is generated according to application execution time prediction model and user demand
Constraint condition nonlinear inequalities or optimization aim, shown in application execution time prediction model such as formula (1)；
Formula (1) indicates a specific Internet of things hardware platform, d={ d using vector d1,d2,...,di, WithAll mainboards, scuta and the peripheral hardware in database are represented, binary selects variable diGeneration
Whether table hardware i is selected, and value is 1 or 0；The user application code for the internet of things equipment operation that U is represented；When running code for the internet of things equipment of Internet of things hardware platform d and user application U specific for one
Between, it can be represented as call Application Programming Interface (Application Programming Interface, API) when
Between tAPI(d), the runing time of non-API codeWith dormancy time tidleThe sum of (U), it can specifically further indicate that are as follows:
Wherein binary selects variable diAnd djRepresent whether hardware i or j are selected, value is 1 or 0；F andIt represents from user's generation
The set of all API and all non-API codes that are obtained in code,WithAll shields of offer APIf in database are provided
Plate and peripheral hardware,Represent the entirety in database, βfWith βuRepresent the operation of the APAnd if non-API code u of passage path weighting
It counts；ti,j,fIt is runing time of the APIf on mainboard i and peripheral hardware j, ti,uIt is runing time of the non-API code on mainboard i；
Φ (U) is the operation that dormancy time is extracted from personal code work；
3.2) generation for applying average power consumption dynamic constrained condition, generates according to using average power consumption prediction model and user demand
Constraint condition nonlinear inequalities or optimization aim, using shown in average power consumption prediction model such as formula (3)；
Wherein binary selects variable diAnd djIt represents hardware or whether is selected, value is 1 or 0, Pi(U) and Pi,j(U) it represents
The average power consumption of hardware i or hardware i, j, specifically may be expressed as: when running code U
It is the energy consumption grade of component i, usesWithRespectively indicate idle energy consumption and activity energy consumption grade
Set, then have (or) with(or) it is that component i or component i exist
In the duty ratio and power consumption values of energy consumption grade k on mainboard j；Duty ratio is the ratio of active time and total time, i.e.,WithWhereinIt is the time that component i is in energy consumption grade k,It is the set for the API that component i is provided,It is that i will be made to enter k-th of energy consumption in the APIf of mainboard j invocation component i
The time span of grade, βfThe operation for representing the APIf of passage path weighting counts,Indicate a circulation institute of operation code
It the time needed, is obtained from step 3.1)；
(4) Internet of things hardware platform static constraint condition, including two indices: hardware platform scalability and price, tool are generated
Steps are as follows for body:
4.1) generation for applying scalability static constraint condition generates constraint according to scalability computation model and user demand
Inequality of condition or optimization aim, shown in scalability computation model such as formula (5)；
The scalability of one specific Internet of things hardware platform d may be expressed as hardware interface surplusAnd MCU pin
SurplusThey can be respectively expressed as:
Wherein binary selects variable diIt represents hardware or whether is selected, value is 1 or 0；WithRepresent database
In all mainboards, scuta and peripheral hardware；WithThe set of physical interface type and interface communication type is respectively represented, i.e.,Each Port occupies two Pin,
AndWithIt is triple<i, W, I>offer/consumption physical interface quantity,WithIt is
Triple<i, W, I>offer/consumption MCU pin quantity；
4.2) generation for applying total price static constraint condition generates constraint according to using total price computation model and user demand
Inequality of condition or optimization aim, using shown in total price computation model such as formula (7)；
WhereinIndicate the price of a specific Internet of things hardware platform d；ciIt is the price of component i；Binary selects variable
diIt representing hardware or whether is selected, value is 1 or 0,WithRepresent all mainboards in database, scuta and outer
If；
(5) optimization problem is solved, the static state being converted in step 3) and step 4), dynamic constrained condition and user are stated
Optimization aim input, matched using the solver of mixed integer nonlinear programming problem by optimal Internet of things hardware is solved
It sets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910356053.XA CN110138604B (en) | 2019-04-29 | 2019-04-29 | Multi-performance-index-oriented automatic generation method for hardware platform of Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910356053.XA CN110138604B (en) | 2019-04-29 | 2019-04-29 | Multi-performance-index-oriented automatic generation method for hardware platform of Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110138604A true CN110138604A (en) | 2019-08-16 |
| CN110138604B CN110138604B (en) | 2020-06-09 |
Family
ID=67575591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910356053.XA Active CN110138604B (en) | 2019-04-29 | 2019-04-29 | Multi-performance-index-oriented automatic generation method for hardware platform of Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110138604B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113821920A (en) * | 2021-09-06 | 2021-12-21 | 重庆大学 | Application scene-oriented Internet of things terminal hardware customization platform and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102271379A (en) * | 2011-05-09 | 2011-12-07 | 陈志奎 | Energy-saving routing method of nodes of internet of things based on context-aware technology |
| CN102663539A (en) * | 2012-03-20 | 2012-09-12 | 昆明悟然科技有限公司 | Operation cost management system based on platform of internet of things |
| CN103973717A (en) * | 2013-01-24 | 2014-08-06 | 中国科学院计算技术研究所 | Internet of things terminal capable of being rebuilt |
| CN105045096A (en) * | 2015-08-26 | 2015-11-11 | 福建恒天晨光节能服务有限公司 | Intelligent energy saving method based on neural network and system thereof |
| CN106027319A (en) * | 2016-07-22 | 2016-10-12 | 中国科学院计算技术研究所 | Simulation IOT resource service system and method |
| US9917903B2 (en) * | 2015-12-28 | 2018-03-13 | Verizon Patent And Licensing Inc. | Internet of things provisioning |
| CN107992339A (en) * | 2017-11-15 | 2018-05-04 | 浙江大学 | A kind of method for automatically generating Internet of things node hardware configuration |
-
2019
- 2019-04-29 CN CN201910356053.XA patent/CN110138604B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102271379A (en) * | 2011-05-09 | 2011-12-07 | 陈志奎 | Energy-saving routing method of nodes of internet of things based on context-aware technology |
| CN102663539A (en) * | 2012-03-20 | 2012-09-12 | 昆明悟然科技有限公司 | Operation cost management system based on platform of internet of things |
| CN103973717A (en) * | 2013-01-24 | 2014-08-06 | 中国科学院计算技术研究所 | Internet of things terminal capable of being rebuilt |
| CN105045096A (en) * | 2015-08-26 | 2015-11-11 | 福建恒天晨光节能服务有限公司 | Intelligent energy saving method based on neural network and system thereof |
| US9917903B2 (en) * | 2015-12-28 | 2018-03-13 | Verizon Patent And Licensing Inc. | Internet of things provisioning |
| CN106027319A (en) * | 2016-07-22 | 2016-10-12 | 中国科学院计算技术研究所 | Simulation IOT resource service system and method |
| CN107992339A (en) * | 2017-11-15 | 2018-05-04 | 浙江大学 | A kind of method for automatically generating Internet of things node hardware configuration |
Non-Patent Citations (1)
| Title |
|---|
| 董玮: "towards rapid and cost-effective prototyping of IoT platforms", 《IEEE》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113821920A (en) * | 2021-09-06 | 2021-12-21 | 重庆大学 | Application scene-oriented Internet of things terminal hardware customization platform and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110138604B (en) | 2020-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Becker et al. | The Palladio component model for model-driven performance prediction | |
| Becker et al. | Model-based performance prediction with the palladio component model | |
| JP2021012734A (en) | System for analyzing prediction data, and method and device related thereto | |
| JP2019023907A (en) | System and technique for predictive data analysis | |
| CN101589366A (en) | Parallelization and instrumentation in a producer graph oriented programming framework | |
| Misra et al. | Weighted Class Complexity: A Measure of Complexity for Object Oriented System. | |
| CN111913713B (en) | Heterogeneous service integration method based on service call tracing | |
| AU2014250921A1 (en) | Assisted creation of control event | |
| Bocciarelli et al. | A model-driven method for building distributed simulation systems from business process models | |
| Adams et al. | A framework for extracting and encoding features from object-centric event data | |
| Zhou et al. | A declarative optimization engine for resource provisioning of scientific workflows in IaaS clouds | |
| Zhao | Some size and structure metrics for quantum software | |
| Hu et al. | Quality model based on ISO/IEC 9126 for internal quality of MATLAB/Simulink/Stateflow models | |
| CN110138604A (en) | A kind of Internet of things hardware platform automatic generation method towards multi-performance index | |
| Deng et al. | Cost-driven autonomous mobility | |
| Mao | Control and data complexity metrics for web service compositions | |
| Wagner | Introduction to simulation using JavaScript | |
| JP7278329B2 (en) | Information processing device, information processing method and program | |
| Nomura et al. | Massive event data analysis and processing service development environment using dfd | |
| Zhu et al. | Sky Computing: Accelerating Geo-distributed Computing in Federated Learning | |
| CN1316359C (en) | User guided program semi-automatic parallelizing method | |
| Bloch et al. | Performance estimation of high-level dataflow program on heterogeneous platforms by dynamic network execution | |
| Thilak et al. | Infusing functional agility in pump industry by using Bluetooth enabled mobile phone | |
| Alzahrani et al. | A formula-driven scalable benchmark model for ABM, applied to FLAME GPU | |
| Concas et al. | Study of the evolution of an agile project featuring a web application using software metrics |
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 |