CN115480243B - Multi-millimeter wave radar end-edge cloud fusion calculation integration and application method thereof - Google Patents
Multi-millimeter wave radar end-edge cloud fusion calculation integration and application method thereof Download PDFInfo
- Publication number
- CN115480243B CN115480243B CN202211077144.8A CN202211077144A CN115480243B CN 115480243 B CN115480243 B CN 115480243B CN 202211077144 A CN202211077144 A CN 202211077144A CN 115480243 B CN115480243 B CN 115480243B
- Authority
- CN
- China
- Prior art keywords
- task
- wave radar
- millimeter wave
- radar
- edge
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000010354 integration Effects 0.000 title claims abstract description 23
- 230000004927 fusion Effects 0.000 title claims abstract description 22
- 238000005070 sampling Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 4
- 230000001419 dependent effect Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000003032 molecular docking Methods 0.000 claims description 6
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 230000000474 nursing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/87—Combinations of radar systems, e.g. primary radar and secondary radar
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/003—Transmission of data between radar, sonar or lidar systems and remote stations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2255—Hash tables
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a multi-millimeter wave radar end-edge cloud fusion calculation integration and a use method thereof, which relate to the multi-millimeter wave radar end-edge cloud fusion calculation integration and mainly comprise the following steps: the terminal side, avris, cloud are surveyed, the terminal side mainly contains different millimeter wave radar terminals, can be with wifi, wired, serial ports mode is connected to on the avris equipment, the avris: the edge computing device is mainly used for millimeter wave radar data processing and computing, the edge device can communicate with the millimeter wave radar device in a wifi (wireless fidelity) wired mode, can communicate with the cloud side server, and can execute radar operation configuration and simple operation parameters issued by the edge, such as starting frequency, fast time, slow time, antenna parameters and sampling frequency of the radar. The invention provides a method for loading, calculating and unloading end-edge cloud tasks, which is suitable for multi-millimeter wave radar access and calculation, and meets the requirement of multi-millimeter wave radar task calculation precedence dependence.
Description
Technical Field
The invention relates to the technical field of millimeter wave radars, in particular to a multi-millimeter wave radar end-edge cloud fusion calculation integration and a use method thereof.
Background
Along with the development of millimeter wave radar technology, the chip technology is advanced, millimeter wave radars with different functions are developed and applied successively in different systems, however, a single millimeter wave radar is difficult to meet the task requirement of a complex scene, and a plurality of identical millimeter wave radars or different millimeter wave radars are required to jointly complete a certain scene task, for example: aiming at the positioning and tracking scene of the millimeter wave radar for the aged in the nursing home, the positioning and tracking scene can be completed by using a plurality of millimeter wave radars together (an FMCW-based millimeter wave radar is deployed every 30m in a corridor, and pulse coherent radars are used in an indoor toilet, so that the non-contact positioning and tracking tasks of the aged in the scene of the nursing home are completed by using different radars together), and therefore, the joint solution of the same or a plurality of tasks by using a plurality of millimeter wave radars is the field of the invention.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a multi-millimeter wave radar end-to-side cloud fusion computing integration and a use method thereof, so as to solve the technical problems in the prior art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: the end edge cloud fusion calculation integration of the multi-millimeter wave radar mainly comprises the following steps: end side, side and cloud measurement;
the terminal side mainly comprises different millimeter wave radar terminals, and can be connected to side equipment in a wifi, wired and serial mode. Meanwhile, the operation configuration and simple operation parameters of the radar issued by the side can be executed, such as the starting frequency, the fast time, the slow time, the antenna parameters and the sampling frequency of the radar are set;
the side is: the edge computing device is mainly capable of performing millimeter wave radar data processing and computing, the edge device can communicate with the millimeter wave radar device in a wifi, wired and serial mode, can communicate with the cloud side server, performs end device registration and edge device registration, acquires an edge device millimeter wave radar computing task, decomposes the task into an executable topology tree, performs end radar basic configuration and distribution after the millimeter wave radar is on line, can compute data submitted by the end millimeter wave radar according to task requirements, and submits a computing result to the cloud. The side equipment can manage the task state according to the millimeter wave radar state required by the task, and timely start and pause the task.
The cloud side mainly refers to an application system server, and can authenticate and manage side and end side equipment, manage side tasks and manage and distribute side task execution results.
The invention also discloses a using method of the multi-millimeter wave radar end edge cloud fusion computing integration, which comprises the following steps:
s1: side registration: the millimeter wave radar edge computing device submits self device information and verification information data to a cloud side, namely a system server. After receiving the registration data, the server manages and maintains the state of the side equipment;
s2: after receiving the registration information of the edge, the server returns the task operated by the edge equipment to the side in the form of metadata, and one side equipment can execute a plurality of millimeter wave radar tasks;
wherein: the metadata refer to task basic information including millimeter wave radar, millimeter wave radar configuration information ConfigInfo, millimeter wave radar dependence tree MMDependcyTree, task calculation logic task OpInfo, and task calculation result submitting server configuration information TaskSubmitInfo;
s3: initializing millimeter wave radar tasks: constructing a multi-millimeter wave radar task topology and a task execution state hash table. And (3) analyzing the metadata information obtained in the step (2), and constructing and initializing a pre-execution environment, wherein the construction flow is as follows:
firstly judging whether the edge equipment meets the execution condition of a task, namely checking the version of the edge computing equipment required by the task, whether operators are all supported, whether the memory is used enough and whether the memory is enough;
initializing a task container according to the task basic information, wherein the container is managed by using an independent process, and distributes required memory for the process, and binds CPU for calculation;
calculating operators used for initializing a topology tree according to a task (each operator is initialized once), checking the correctness of the topology tree (checking whether the parameter entering type is proper or not and the parameter exiting type), placing the operators with related initialization in an operator pool, and directly copying or referring from the operator pool when the operators are used later, wherein the operators in the operator pool are not destroyed;
and d, constructing a task execution state identifier, binding the task execution state identifier to a process to be used as a global variable, and constructing a task dependent millimeter wave Hash table according to a task dependent millimeter wave radar tree.
And S4, registering the millimeter wave radar, and after the millimeter wave radar is communicated with the edge equipment, transmitting the physical information and the equipment information of the millimeter wave radar to the edge equipment for registering. After successful registration, the Hash table dependent on the millimeter wave radar is updated, and the task state is modified into a waiting state. The millimeter wave radar may be used in different tasks, and the side device may sequentially determine and modify the Hash table according to the millimeter wave radar dependency tree. If the millimeter wave radar on which the millimeter wave radar calculation task depends is ready, the task state is changed to be enabled at the moment. Otherwise, the operation is suspended;
s5, radar configuration: the side equipment sends radar configuration parameters to the millimeter wave radar, and the radar carries out radar related configuration and starts to work after receiving the configuration parameters;
s6, uploading radar data: after the radar works, sampling the filtered and basic operation (difference frequency, iq modulation) according to the corresponding sampling frequency, and then sending the sampled radar to side equipment;
s7, executing tasks according to the task topology and the hash table: and after receiving the data, the side equipment firstly judges whether the current task state is enabled, and if yes, the side equipment calculates according to the topology tree. The specific calculation process is as follows:
initializing a result temporary storage register of the current calculation;
adding operators into an execution queue sequentially according to the sequence from top to bottom, left to right, and if the current queue exists, building no more in the next calculation;
c, according to the operator type of the dequeue in the queue, taking out the operator from the operator pool, setting the operator to zero (clearing the last calculation state), taking out the operator output parameter from the result register, executing operator calculation, and putting the result in the temporary register after the calculation is completed;
and D, when the queue is empty, indicating that the task is finished, and outputting a result.
S8, submitting task calculation results: and checking and packaging the docking result, and uploading the docking result to the cloud side server according to the configuration information of the submitting server.
As the preferable technical scheme of the invention, the task BaseInfo mainly comprises a task name, a task unique identifier UUID, whether a task process can be interrupted, whether the process can be recovered, the maximum waiting time of the task starting, a version, a required memory and task context time data.
As a preferred technical solution of the present invention, configmnfo is a configuration of the millimeter wave Lei Dacan number, mainly comprising: radar antenna correlation configuration, transmit power configuration, transmit frequency configuration, sample correlation configuration, configuration for each radar containing a configuration unique number and a configuration used radar. The configuration can control the function of a receiving and transmitting antenna of the millimeter wave radar and the data output content.
As a preferred technical scheme of the invention, the MMDependencyTree is a dependency tree between tasks and millimeter wave radars and radar configuration, and the form of the MMDependencyTree is shown in figure 4: each task may rely on the output of multiple millimeter wave radar data.
As a preferred technical scheme of the invention, the TaskOpInfo is millimeter wave radar task calculation logic, and is described by using a calculation topology tree, wherein the calculation topology tree refers to a calculation tree which is formed by compiling related calculation logic and has a direction and can represent operator execution sequence and output. For example. The basic units of the computation tree are operators and connecting lines with arrows, the arrows point to the operators and represent the outputs of the operators, the arrows point out the outputs representing the operators from the operators, and the operators can only have one output but can be simultaneously used as the outputs of other operators. If the operator has multiple parameters, the operator will only work if multiple parameters are present at the same time.
As a preferred technical scheme of the invention, the TaskSubmitInfo is related configuration information for submitting the last output content of the task to the server, and comprises a submitting path (URI) of the server, a submitting mode, a submitting frequency, whether the last output content is submitted as stream data or not, and whether the last output content is submitted as content with time information.
The invention provides a multi-millimeter wave radar end edge cloud fusion calculation integration and a use method thereof, which have the following beneficial effects:
the invention provides a method for loading, calculating and unloading end-edge cloud tasks, which is suitable for multi-millimeter wave radar access and calculation, and meets the requirement of multi-millimeter wave radar task calculation precedence dependence.
Drawings
Fig. 1 is a graph of a multi-millimeter-wave radar end-edge cloud fusion calculation integration;
fig. 2 is a logic computation topology tree of millimeter wave radar task computation in the multi-millimeter wave radar end-edge cloud fusion computation integration;
fig. 3 is a flowchart of initializing a millimeter wave radar task in the method for using the end-edge cloud fusion calculation integration of the multi-millimeter wave radar;
fig. 4 is a dependency tree between tasks and millimeter wave radars and radar configuration in the multi-millimeter wave radar end-edge cloud fusion calculation integration.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings and examples. The following examples are illustrative of the invention but are not intended to limit the scope of the invention.
Examples
Referring to fig. 1, the present invention provides a technical solution: the end edge cloud fusion calculation integration of the multi-millimeter wave radar mainly comprises the following steps: end side, side and cloud measurement;
the terminal side mainly comprises different millimeter wave radar terminals, and can be connected to side equipment in a wifi, wired and serial mode. Meanwhile, the operation configuration and simple operation parameters of the radar issued by the side can be executed, such as the starting frequency, the fast time, the slow time, the antenna parameters and the sampling frequency of the radar are set;
the side is: the edge computing device is mainly capable of performing millimeter wave radar data processing and computing, the edge device can communicate with the millimeter wave radar device through wifi, a wired side and a serial port, can communicate with a cloud side server, performs end device registration and edge device registration, acquires an edge device millimeter wave radar computing task, decomposes the task into an executable topology tree, performs end radar basic configuration and distribution after the millimeter wave radar is on line, can compute data submitted by the end millimeter wave radar according to task requirements, and submits a computing result to a cloud. The side equipment can manage the task state according to the millimeter wave radar state required by the task, and timely start and pause the task.
The cloud side mainly refers to an application system server, and can authenticate and manage side and end side equipment, manage side tasks and manage and distribute side task execution results.
The invention also discloses a using method of the multi-millimeter wave radar end edge cloud fusion computing integration, which comprises the following steps:
s1: side registration: the millimeter wave radar edge computing device submits self device information and verification information data to a cloud side, namely a system server. After receiving the registration data, the server manages and maintains the state of the side equipment;
s2: after receiving the registration information of the edge, the server returns the task operated by the edge equipment to the side in the form of metadata, and one side equipment can execute a plurality of millimeter wave radar tasks;
wherein: the metadata refer to task basic information including millimeter wave radar, millimeter wave radar configuration information ConfigInfo, millimeter wave radar dependence tree MMDependcyTree, task calculation logic task OpInfo, and task calculation result submitting server configuration information TaskSubmitInfo;
s3: initializing millimeter wave radar tasks: as shown in fig. 3, the construction of the multi-millimeter wave radar task topology and the construction of the task execution state hash table, by analyzing the metadata information acquired in S2, the construction and initialization construction flow of the pre-execution environment is as follows:
firstly judging whether the edge equipment meets the execution condition of a task, namely checking the version of the edge computing equipment required by the task, whether operators are all supported, whether the memory is enough and whether the memory is enough, wherein the operators are a mapping O from a function space to a function space: the operator in the broad sense of X-X can be popularized to any space, such as inner product space and the like;
initializing a task container according to the task basic information, wherein the container is managed by using an independent process, and distributes required memory for the process, and binds CPU for calculation;
calculating operators used for initializing a topology tree according to a task (each operator is initialized once), checking the correctness of the topology tree (checking whether the parameter entering type is proper or not and the parameter exiting type), placing the operators with related initialization in an operator pool, and directly copying or referring from the operator pool when the operators are used later, wherein the operators in the operator pool are not destroyed;
and d, constructing a task execution state identifier, binding the task execution state identifier to a process to be used as a global variable, and constructing a task dependent millimeter wave Hash table according to a task dependent millimeter wave radar tree.
And S4, registering the millimeter wave radar, and after the millimeter wave radar is communicated with the edge equipment, transmitting the physical information and the equipment information of the millimeter wave radar to the edge equipment for registering. After successful registration, the Hash table dependent on the millimeter wave radar is updated, and the task state is modified into a waiting state. The millimeter wave radar may be used in different tasks, and the side device may sequentially determine and modify the Hash table according to the millimeter wave radar dependency tree. If the millimeter wave radar on which the millimeter wave radar calculation task depends is ready, the task state is changed to be enabled at the moment. Otherwise, the operation is suspended;
s5, radar configuration: the side equipment sends radar configuration parameters to the millimeter wave radar, and the radar carries out radar related configuration and starts to work after receiving the configuration parameters;
s6, uploading radar data: after the radar works, sampling the filtered and basic operation (difference frequency, iq modulation) according to the corresponding sampling frequency, and then sending the sampled radar to side equipment;
s7, executing tasks according to the task topology and the hash table: and after receiving the data, the side equipment firstly judges whether the current task state is enabled, and if yes, the side equipment calculates according to the topology tree. The specific calculation process is as follows:
initializing a result temporary storage register of the current calculation;
adding operators into an execution queue sequentially according to the sequence from top to bottom, left to right, and if the current queue exists, building no more in the next calculation;
c, according to the operator type of the dequeue in the queue, taking out the operator from the operator pool, setting the operator to zero (clearing the last calculation state), taking out the operator output parameter from the result register, executing operator calculation, and putting the result in the temporary register after the calculation is completed;
and D, when the queue is empty, indicating that the task is finished, and outputting a result.
S8, submitting task calculation results: and checking and packaging the docking result, and uploading the docking result to the cloud side server according to the configuration information of the submitting server.
The task BaseInfo mainly comprises a task name, a task unique identifier UUID, whether a task process can be interrupted or not, whether the process can be recovered, a task starting maximum waiting time, a version, a required memory and task context time data.
Wherein, configInfo is the configuration of the millimeter wave Lei Dacan number, mainly comprising: radar antenna correlation configuration, transmit power configuration, transmit frequency configuration, sample correlation configuration, configuration for each radar containing a configuration unique number and a configuration used radar. The configuration can control the function of a receiving and transmitting antenna of the millimeter wave radar and the data output content.
The mmdependencystment is a dependency tree between tasks and millimeter wave radars and radar configuration, and the form of the mmdependencystment is shown in fig. 4: each task may rely on the output of multiple millimeter wave radar data.
In fig. 4, task 1-configuration 1-radar 1, which means that the calculation process of task 1 depends on millimeter wave radar 1, and that the radar is configured using configuration 1.
Task 1 and task 2 together rely on a radar 2 and use different configurations, wherein the two different configurations must have an inclusion relationship, namely: configuration 1 is contained in configuration 2 or configuration 2 is contained in configuration 1.
As shown in FIG. 2, taskOpInfo is millimeter wave radar task calculation logic, and is described by using a calculation topology tree, wherein the calculation topology tree refers to a calculation tree which is formed by compiling related calculation logic and has a direction and can represent operator execution sequence and output. For example. The basic units of the computation tree are operators and connecting lines with arrows, the arrows point to the operators and represent the outputs of the operators, the arrows point out the outputs representing the operators from the operators, and the operators can only have one output but can be simultaneously used as the outputs of other operators. If the operator has multiple parameters, the operator will only work if multiple parameters are present at the same time.
The tasksubmicron info is related configuration information for submitting the last output content of the task to the server, and comprises a submitting path (URI) of the server, a submitting mode, a submitting frequency, whether the last output content is submitted as stream data or not, and whether the last output content is submitted as the content with time information.
The invention provides a multi-millimeter wave radar integration, scheduling, calculation and communication method under the end-edge cloud cooperative calculation technology. The end Bian Yun cooperative computing is an emerging computing mode, has attracted extensive attention in academia and industry, and related content of Bian Yun cooperation is already contained in white paper published by MEC ISG working group established in 2014, and important attention is focused on end cloud cooperative computing in Internet of things edge computing platforms sequentially published by Amazon, microsoft, hua Cheng, *** enterprises and the like. The task unloading focuses on the flow of computational power demands and the distribution of calculation and storage resources in the cooperative calculation of the end Bian Yun, determines the calculation topology of the task, predicts the task assistance, and is helpful for improving the execution efficiency of the edge end and reducing the important effect of time delay.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, shall cover the same or different embodiments according to the technical solution and the inventive concept of the present invention. It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (7)
1. The end edge cloud fusion calculation integration of the multi-millimeter wave radar is characterized by mainly comprising: end side, side and cloud side;
the terminal side mainly comprises different millimeter wave radar terminals, can be connected to side equipment in a wifi, wired and serial mode, and can execute radar running configuration and simple operation parameters issued by the side, such as starting frequency, fast time, slow time, antenna parameters and sampling frequency of the radar;
the side is: the edge computing device is mainly capable of performing millimeter wave radar data processing and computing, the edge device can communicate with the millimeter wave radar device in a wifi, wired and serial mode, can communicate with the cloud side server, performs end device registration and edge device registration, acquires an edge device millimeter wave radar computing task, decomposes the edge device millimeter wave radar computing task into an executable topology tree, performs end radar basic configuration and distribution after the millimeter wave radar is online, can compute data submitted by the end millimeter wave radar according to task requirements, submits the computing result to a cloud, and the edge device can perform task state management according to the millimeter wave radar state required by the task and timely starts and pauses the task;
the cloud side is an application system server, and can authenticate and manage side and end side equipment, manage side tasks and manage and distribute side task execution results.
2. The method for using the multi-millimeter wave radar end-edge cloud fusion computing integration according to claim 1, comprising the following steps:
s1: side registration: the millimeter wave radar edge computing equipment submits self equipment information and verification information data to a cloud side, namely a system server, and the server carries out management and state maintenance of side equipment after receiving registration data;
s2: after receiving the registration information of the edge, the server returns the task operated by the edge equipment to the side in the form of metadata, and one side equipment can execute a plurality of millimeter wave radar tasks;
wherein: the metadata refer to task basic information including millimeter wave radar, millimeter wave radar configuration information ConfigInfo, millimeter wave radar dependence tree MMDependcyTree, task calculation logic task OpInfo, and task calculation result submitting server configuration information TaskSubmitInfo;
s3: initializing millimeter wave radar tasks: constructing a multi-millimeter wave radar task topology and a task execution state hash table, and analyzing the metadata information acquired in the step 2 to construct and initialize a pre-execution environment, wherein the construction flow is as follows:
firstly judging whether the edge equipment meets the execution condition of a task, namely checking the version of the edge computing equipment required by the task, whether operators are all supported, whether the memory is used enough and whether the memory is enough;
initializing a task container according to the task basic information, wherein the container is managed by using an independent process, and distributes required memory for the process, and binds CPU for calculation;
c, calculating operators used for initializing a topology tree according to a task, initializing each operator once, checking the correctness of the topology tree, checking whether a parameter entering type is proper or not, outputting the parameter type, putting the operators with related initialization in an operator pool, and directly copying or referring from the operator pool when in later use, wherein the operators in the operator pool are not destroyed;
constructing a task execution state identifier, binding the task execution state identifier to a process to be used as a global variable, and constructing a millimeter wave-dependent Hash table of the task according to a task-dependent millimeter wave radar tree;
s4, after the millimeter wave radar is registered and communicated with the edge equipment, the millimeter wave radar firstly sends own physical information and equipment information to the edge equipment for registration, after the registration is successful, a Hash table which is dependent on the millimeter wave radar is updated, the task state is modified to be a waiting state, the millimeter wave radar can be used in different tasks, at the moment, the side equipment can judge and modify the Hash table in sequence according to the millimeter wave radar dependency tree, if the millimeter wave radar on which the millimeter wave radar calculates the task is ready, at the moment, the task state is changed to be started, otherwise, the task is stopped;
s5, radar configuration: the side equipment sends radar configuration parameters to the millimeter wave radar, and the radar carries out radar related configuration and starts to work after receiving the configuration parameters;
s6, uploading radar data: after the radar works, sampling the filtered and basic operation according to the corresponding sampling frequency, and then sending the sampled radar to side equipment;
s7, executing tasks according to the task topology and the Hash table: after receiving the data, the side equipment firstly judges whether the current task state is enabled, and if yes, the side equipment calculates according to the topology tree; the specific calculation process is as follows:
initializing a result temporary storage register of the current calculation;
adding operators into an execution queue sequentially according to the sequence from top to bottom, left to right, and if the current queue exists, building no more in the next calculation;
c, according to the operator type of the dequeue in the queue, taking out the operator from the operator pool, setting the operator to zero, clearing the last calculation state, taking out the operator output parameter from the result register, executing the operator calculation, and putting the result in the temporary register after the calculation is completed;
d, when the queue is empty, indicating that the task is executed, and outputting a result;
s8, submitting task calculation results: and checking and packaging the docking result, and uploading the docking result to the cloud side server according to the configuration information of the submitting server.
3. The method for using the multi-millimeter-wave radar end-edge cloud fusion computing integration according to claim 2, wherein task basic information TaskBaseInfo of the millimeter-wave radar mainly comprises task names, task unique identifiers (UUIDs), whether task processes can be interrupted, whether processes can be recovered, maximum waiting time of task starting, version, required memory and task context time data.
4. The method for using the multi-millimeter-wave radar end-edge cloud fusion computing integration according to claim 2, wherein the millimeter-wave radar configuration information configmfo is a configuration of millimeter waves Lei Dacan number, and mainly comprises: the method comprises the steps of radar antenna related configuration, transmitting power configuration, transmitting frequency configuration, sampling related configuration, wherein each configuration of millimeter wave radar parameters comprises a configuration unique number and millimeter wave radar used by configuration, and the configuration can control the function of a receiving and transmitting antenna and data output content of the millimeter wave radar.
5. The method for using the multi-millimeter-wave radar end-edge cloud fusion computing integration according to claim 2, wherein the millimeter-wave radar dependency tree MMDependorTree is a dependency tree between tasks and millimeter-wave radar and radar configuration, and each task can depend on output of a plurality of millimeter-wave radar data.
6. The method for using the multi-millimeter-wave radar end-edge cloud fusion computing integration according to claim 2, wherein the task computing logic taskop info is millimeter-wave radar task computing logic and is described by using a computing topology tree, and the computing topology tree is a computing tree which is formed by compiling related computing logic and has a direction and can represent operator execution sequence and output.
7. The method for using the multi-millimeter-wave radar end-edge cloud fusion computing integration according to claim 2, wherein the task computing result submitting server configuration information tasksumitinfo is related configuration information for submitting the last output content of the task to the server, and includes a submitting path, a submitting mode and a submitting frequency of the server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211077144.8A CN115480243B (en) | 2022-09-05 | 2022-09-05 | Multi-millimeter wave radar end-edge cloud fusion calculation integration and application method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211077144.8A CN115480243B (en) | 2022-09-05 | 2022-09-05 | Multi-millimeter wave radar end-edge cloud fusion calculation integration and application method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115480243A CN115480243A (en) | 2022-12-16 |
CN115480243B true CN115480243B (en) | 2024-02-09 |
Family
ID=84393073
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211077144.8A Active CN115480243B (en) | 2022-09-05 | 2022-09-05 | Multi-millimeter wave radar end-edge cloud fusion calculation integration and application method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115480243B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007232411A (en) * | 2006-02-27 | 2007-09-13 | Toyota Motor Corp | Object detecting apparatus |
CN110022234A (en) * | 2019-04-16 | 2019-07-16 | 中国人民解放军国防科技大学 | Method for realizing unstructured data sharing mechanism facing edge calculation |
CN111681418A (en) * | 2020-05-26 | 2020-09-18 | 南京信息职业技术学院 | Road state monitoring system based on multiple millimeter wave radars and working method thereof |
US11089083B1 (en) * | 2019-11-04 | 2021-08-10 | Edjx, Inc. | Systems and methods for locating microserver nodes in proximity to edge devices using georouting |
CN216873319U (en) * | 2022-02-23 | 2022-07-01 | 深圳市旗扬特种装备技术工程有限公司 | Thunder look fuses road monitored control system |
WO2022141910A1 (en) * | 2021-01-01 | 2022-07-07 | 杜豫川 | Vehicle-road laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field |
-
2022
- 2022-09-05 CN CN202211077144.8A patent/CN115480243B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007232411A (en) * | 2006-02-27 | 2007-09-13 | Toyota Motor Corp | Object detecting apparatus |
CN110022234A (en) * | 2019-04-16 | 2019-07-16 | 中国人民解放军国防科技大学 | Method for realizing unstructured data sharing mechanism facing edge calculation |
US11089083B1 (en) * | 2019-11-04 | 2021-08-10 | Edjx, Inc. | Systems and methods for locating microserver nodes in proximity to edge devices using georouting |
CN111681418A (en) * | 2020-05-26 | 2020-09-18 | 南京信息职业技术学院 | Road state monitoring system based on multiple millimeter wave radars and working method thereof |
WO2022141910A1 (en) * | 2021-01-01 | 2022-07-07 | 杜豫川 | Vehicle-road laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field |
CN216873319U (en) * | 2022-02-23 | 2022-07-01 | 深圳市旗扬特种装备技术工程有限公司 | Thunder look fuses road monitored control system |
Non-Patent Citations (2)
Title |
---|
"Edge Element Calculation of Radar Cross Section of Small Maritime Targets with Respect to Height of Radar Antenna";H. Dodig等;《the International Journal on Marine Navigation and Safety of Sea Transportation》;第14卷(第2期);331-336 * |
"面向智慧交通的图像处理与边缘计算";曹行健等;《中国图像图形学报》;1743-1767 * |
Also Published As
Publication number | Publication date |
---|---|
CN115480243A (en) | 2022-12-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10613788B2 (en) | Data migration between cloud storage systems | |
CN107145380B (en) | Virtual resource arranging method and device | |
US9841988B1 (en) | Updating service virtual machines using a new image that is certified | |
US20170163479A1 (en) | Method, Device and System of Renewing Terminal Configuration In a Memcached System | |
US20170163478A1 (en) | Method,electronic device and system for updating client configuration in key-value pair database | |
US20120197990A1 (en) | Publish-subscribe messaging | |
CN104731595A (en) | Big-data-analysis-oriented mixing computing system | |
CN111984408B (en) | Data cooperative processing method based on big data and edge computing and edge cloud platform | |
CN104067231A (en) | Controlling a network interface using virtual switch proxying | |
CN114500623B (en) | Network target range interconnection and intercommunication method, device, equipment and readable storage medium | |
CN108491278B (en) | Method and network device for processing service data | |
CN110245029A (en) | A kind of data processing method, device, storage medium and server | |
CN109104368B (en) | Connection request method, device, server and computer readable storage medium | |
CN111782730A (en) | File uploading method and device and storage medium | |
CN115480243B (en) | Multi-millimeter wave radar end-edge cloud fusion calculation integration and application method thereof | |
CN102082816B (en) | File transmission method and transmission engines and network elements | |
CN110661780A (en) | Wireless city data sharing method and system based on SAAS application | |
CN117931478A (en) | Inter-process communication method, inter-process communication device and storage medium | |
CN110324194B (en) | Method, apparatus, system and medium for load balancing | |
CN108833532B (en) | Service processing method, device and system based on Internet of things | |
CN115061091A (en) | Radar data processing method and system and electronic equipment | |
WO2023044673A1 (en) | Method and apparatus for deploying industrial edge application, and computer-readable storage medium | |
CN114564210A (en) | Copy deployment method, device, system, electronic equipment and storage medium | |
CN112766486A (en) | Searching method of neural network structure, terminal, server and readable storage medium | |
CN113268360A (en) | Request processing method, device, server and storage medium |
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 |