CN110430591B - Intelligent deployment and reconstruction method for baseband resource pool - Google Patents
Intelligent deployment and reconstruction method for baseband resource pool Download PDFInfo
- Publication number
- CN110430591B CN110430591B CN201910810868.0A CN201910810868A CN110430591B CN 110430591 B CN110430591 B CN 110430591B CN 201910810868 A CN201910810868 A CN 201910810868A CN 110430591 B CN110430591 B CN 110430591B
- Authority
- CN
- China
- Prior art keywords
- deployment
- resource pool
- resource
- resources
- reconstruction
- 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
Images
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
- H04L41/50—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
- H04L41/5048—Automatic or semi-automatic definitions, e.g. definition templates
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Stored Programmes (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses an intelligent deployment and reconstruction method of a baseband resource pool, and aims to provide a method for rapidly, efficiently and adaptively allocating software and hardware resources to complete deployment and reconstruction of a cross-platform baseband resource pool. The invention is realized by the following technical scheme: a plurality of chassis/board cards are interconnected through optical fibers/Ethernet/cables to form a distributed baseband resource pool processing system; the baseband resource pool processing system provides a set of programmable task templates and a set of editable resource pool logic equipment library; the base band resource pool receives the task instruction, completes corresponding software and hardware resource matching in the task template and the logic equipment library, generates a set of resource deployment scheme, a plurality of optional schemes and corresponding evaluation parameters, and can intervene in selection by a user; the resource pool finishes the loading of the application function component according to the deployment scheme; when the task and the resource change or the platform fails, the system adaptively calls a reconstruction strategy, the reconstruction strategy is an open editable script, and the script can be dynamically updated according to needs.
Description
Technical Field
The invention relates to a comprehensive electronic information system used in the fields of communication, measurement and control and the like, which can rapidly and efficiently automatically allocate software and hardware resources according to function and resource changes and complete intelligent deployment and reconstruction of software and hardware configuration of a cross-platform baseband resource pool.
Background
The deployment and reconstruction of the baseband resource pool are essentially how to solve the problem of dynamic configuration of cross-platform system resources. There are many mapping modes for mapping a logic system to a real physical system, and this mapping process needs to comprehensively consider a series of system requirements and limitations, such as real-time problem, memory problem, communication problem, etc.; on the other hand, due to the switching of the loading function, the system reconfiguration and remapping processes caused by software and hardware faults also have great diversity and uncertainty. Currently, a static configuration mode is mostly adopted for deployment and reconfiguration methods of a baseband resource pool, a reconfiguration strategy and a mapping relation are standardized in advance before a system operates, the mapping process from a logic system to a real physical system becomes more and more complex along with the continuous increase of the scale of the system, and particularly for an open-type and growing integrated electronic integrated system, when new functions or resources are added into the system, the configuration mode of the strategy and the mapping relation which are standardized in advance cannot adapt to the change quickly. Therefore, a new method for deploying and reconstructing a baseband resource pool needs to be researched, which can quickly adapt to the change of functions and resources of a cross-platform system, and minimize the influence of the change on the system.
Disclosure of Invention
The invention aims to provide a method for rapidly, efficiently and adaptively allocating software and hardware resources according to functional requirements and equipment available resource changes to finish the deployment and reconstruction of a cross-platform baseband resource pool, aiming at the defect that the conventional baseband resource pool can only realize the deployment and reconstruction method based on a preset configuration library.
The above object of the present invention can be achieved by the following measures: an intelligent deployment and reconstruction method of a baseband resource pool has the following technical characteristics: a plurality of baseband resource pool chassis/board cards are interconnected through optical fibers/Ethernet/cables to form a distributed baseband resource pool processing system with multiple computing resources and processing resources, and a set of programmable task templates and a set of editable resource pool logic equipment library are provided; the base band resource pool receives the task instruction, adapts the corresponding instruction in the task template, the resource pool logic equipment base matches the corresponding hardware resource according to the input data of the task template, completes the matching of the software and hardware resources, generates a set of resource deployment scheme, a plurality of alternatives and corresponding evaluation parameters, and the deployment scheme can be selected by the user in an intervention way; and the resource pool finishes the loading of the application function component according to the resource deployment view scheme, realizes the mapping from the platform logic system to the real physical system, and finishes the configuration of the cross-platform baseband resource pool and the intelligent reconstruction and deployment of the baseband resource pool.
Compared with the prior art, the invention has the following beneficial effects:
the invention adopts the hardware environment that the chassis/board card are interconnected through the optical fiber/Ethernet/cable, utilize a plurality of chassis to form the resource processing pool of distributed baseband, include resources such as the multi-type processing resource (resources such as universal processor PowerPC, ZYNQ, FPGA, DSP, etc.) in the processing pool, every chassis can bear the weight of the functional application independently, can cooperate and finish the implement of the functional application each other. The system can automatically allocate software and hardware resources rapidly and efficiently according to the change of the demand and the available resources of the equipment, complete the deployment of the cross-platform baseband resource pool configuration, improve the resource utilization rate and reduce the construction and operation and maintenance costs.
According to the invention, the matching of software and hardware resources is completed in the resource pool logic equipment library according to the application data input of the task template, a set of resource deployment scheme and a plurality of optional schemes and corresponding evaluation parameters are generated, the user of the deployment scheme can intervene in selection, and the resource pool realizes the mapping from the platform logic system to the real physical system according to the selection of the deployment scheme, thereby completing the functional application loading. And finally, the software and hardware resources are rapidly and efficiently distributed in a self-adaptive manner, and the deployment and the reconstruction of the cross-platform baseband resource pool are completed. The test result shows that the virtualized baseband card is improved in the aspects of reconstruction time, typical data transmission time delay, transmission performance and the like.
The resource pool logic equipment library matches corresponding hardware resources according to the input data of the task template, completes the matching of software and hardware resources, generates a set of resource deployment scheme, a plurality of optional schemes and corresponding evaluation parameters, and the baseband resource pool processing system enhances the centralized management capability of the resource pool system on functional application through a set of task templates which can be arranged. The problems of huge hardware configuration, low universality and resource configuration and the like of ground equipment in the prior art are solved.
Drawings
Fig. 1 is a schematic diagram of a distributed baseband resource pool enclosure network according to the present invention.
Fig. 2 is a schematic diagram of an intelligent deployment process of the baseband resource pool according to the present invention.
Fig. 3 is a schematic diagram of a baseband resource pool chassis processing circuit of the baseband resource pool of fig. 1.
Fig. 4 is a schematic diagram of the intelligent reconfiguration process of the baseband resource pool according to the present invention.
The invention is further described with reference to the following figures and examples.
Detailed Description
Refer to fig. 1 and 2. According to the invention, a plurality of baseband resource pool chassis/board cards are interconnected through optical fibers/Ethernet/cables to form a distributed baseband resource pool processing system with multiple computing resources and processing resources, and a set of programmable task templates and a set of editable resource pool logic equipment library are provided; the base band resource pool receives the task instruction, adapts the corresponding instruction in the task template, and the resource pool logic device library matches the corresponding hardware resource according to the input data of the task template, so as to complete the matching of the software resource and the hardware resource, and generate a set of resource deployment scheme, a plurality of alternatives and corresponding evaluation parameters; and the resource pool can be selected by user intervention according to the resource deployment view scheme, so that the loading of the application function component is completed, the mapping from the platform logic system to the real physical system is realized, and the configuration of the cross-platform baseband resource pool and the intelligent reconstruction and deployment of the baseband resource pool are completed.
The hardware environment of the baseband resource pool is a distributed processing pool consisting of a plurality of baseband resource pool cases, the baseband resource pool cases/board cards are interconnected through optical fibers/Ethernet/cables, each baseband resource pool case/board card contains various processing resources such as ZYNQ, FPGA, multichannel digital signal processing DSP and the like, each ZYNQ, FPGA, DSP and PowerPC are interconnected through a RapidIO bus, and each ZYNQ and PPC are interconnected through a gigabit network. The baseband resource pool chassis can independently bear functional application and can also be matched with each other to finish the realization of the functional application.
When the task and the resource change or the platform fails, the baseband resource pool processing system adaptively adapts the reconstruction strategy, dynamically allocates appropriate resources according to the corresponding reconstruction strategy to complete the remapping and reloading of the system, and the reconstruction strategy is an open and editable script and can be dynamically updated as required.
The reconstruction strategy comprises but is not limited to a load balancing reconstruction strategy based on algorithms such as weighted polling, random, minimum response time, minimum concurrency number and Hash, a machine learning reconstruction strategy based on algorithms such as linear regression, logistic regression, decision tree, random forest, bayes, greedy algorithm, simulated annealing and the like, and other strategies, and the baseband resource pool processing system dynamically allocates appropriate resources according to the corresponding algorithm reconstruction strategy to complete the remapping and reloading of the system.
The task scheduling template is used for inputting the composition of each application function component, the port connection relation, the description of the requirements of hardware resource memory, processing capacity, communication bandwidth, instantaneity and the like; the logic device library is used for listing information such as types, storage capacity, communication capacity, operation speed and the like of each hardware in the resource pool.
See fig. 3. The baseband resource pool case comprises a plurality of signal processing modules and a management control module which are interconnected through RapidIO buses and Ethernet, wherein the signal processing modules can adopt an architecture which is based on interconnection of an analog-digital converter/digital-analog converter AD/DA, a Soc device ZYNQ, a field programmable gate array FPGA and a digital signal processor DSP, the management control module mainly comprises a PowerPC, the management control module externally provides interfaces such as a debugging port, a serial port and a network port, the ZYNQ, the FPGA, the DSP and the PowerPC in the case are interconnected through the RapidIO buses, and the ZYNQ and the PPC are interconnected through a gigabit network. The chassis provides interfaces including but not limited to radio frequency, gigabit port, gigabit, debug, optical port, etc.
In an alternative embodiment, a load balancing method with the minimum root mean square deviation of resource occupancy rate is taken as an example to illustrate the reconstruction and deployment of the baseband resource pool. In the reconstruction and deployment of the baseband resource pool, N =1,2, \8230;, N denotes the chassis number of the baseband resource pool, M =1,2, \8230;, M denotes the identification of different classes of resources, wherein M =1 denotes a DSP type resource, M =2 denotes an FPGA type resource, M =3 denotes a PowerPC type resource, w denotes a FPGA type resource, and nm representing the total number of M classes of resources in the chassis N by using a matrix with dimension of NxM
Representing the total number set of various resources in each chassis by using a matrix with dimension of NxM
Representing the occupation amount set of various resources in each case in the current state, wherein d nm Representing m classes in a chassis nD is more than or equal to 0 nm ≤w nm (ii) a Using matrices of dimension NxM
Representing the occupancy rate set of various resources in each chassis in the current state, wherein nm Indicating the occupancy of the m types of resources in the chassis n,
using vectors P of dimension 1 × M 0 ＝[p 1 p 2 ... p M ]The average value set represents the occupancy rates of various resources in each case in the current state, wherein p m The average value of the occupancy rates of the m-th type resources in each chassis in the current state is shown,
t =1,2,3, \ 8230;, T, T functional components com (1), com (2), com (3), com (4), \8230;, com (T) constitute the application S, each functional component only corresponds to one type of hardware resource, the types and external constraints of the hardware resources corresponding to com (4), \8230;, com (T) are known from the task template, R represents the number of hardware resource deployment schemes capable of bearing the application S, R =1,2,3, \8230, R represents a matrix with dimension R × T in the resource pool logical device library
Representing the chassis number corresponding to each functional component in each deployment scenario, wherein z rt Represents the chassis number corresponding to the component com (t) in the r deployment schemes, and z is more than or equal to 1 rt N is less than or equal to N; using matrices of dimension R x T
Representing the chip number of each functional component in each deployment plan in the corresponding chassis, wherein z rt ' denotes the r arrangement, where the component com (t) is in the cabinet z rt The chip number in (1) is included,
according to the running state of the resource pool, the hardware number Z related to the occupied current hardware resource in the matrix Z' is numbered rt ' delete, delete at the same time z rt ' line of position z r 'and Z' of the correlation matrix Z r Rows to ensure that all resources in the matrix Z, Z' are in an idle state. Using a vector Q of dimension 1 × M r ＝[q 1 q 2 ... q M ]Representation based on scheme z r 、z r ' the occupancy rates of various resources in each case after deployment and the occupancy rates of various resources in each case in the original state are in a root-mean-square deviation set, wherein q is m Representation based on scheme z r 、z r ' the occupancy rate of the m-th type resource in each chassis after deployment is deviated from the root mean square of the occupancy rate of the m-th type resource in each chassis in the original state,
l of' nm Representation is based on scheme z r 、z r ' occupancy rate set of various resources in each chassis after deployment, pm represents a scheme z-based r 、z r ' average value of occupancy rate of m-th type resource before deployment in each chassis. Defining an evaluation function f = MAX (Q) r ) The return value of the function f is the matrix Q r Maximum value of (2)
Taking any one deployment scheme from the matrixes Z and Z': z is a radical of formula r 、z r ', calculating: z is a radical of r 、z r ' the occupancy rates of various resources in each case after the represented deployment scheme is deployed and the root mean square deviation vector Q of the occupancy rates of various resources in the original state in each case r ＝[q 1 q 2 ... q M ]Introduction of Q into r Substituting evaluation function f = MAX (Q) r ) And then taking the deployment scheme from the matrix Z and Z': z is a radical of formula r+1 、z r+1 ', calculating z r+1 、z r+1 ' the deployment scenario represented deploys various types of assetsRoot mean square deviation vector Q of source occupancy rate in each case and occupancy rate of various resources in original state in each case r+1 ＝[q 1 q 2 ... q M ]Introduction of Q into r+1 Carry-in evaluation function f r+1 ＝MAX(Q r+1 ). Sequentially traversing all the deployment schemes, and finally obtaining a function f r And the deployment scheme corresponding to the minimum return value is the optimal deployment scheme.
See fig. 4. The baseband resource pool reconstruction is divided into three types, namely task reconstruction, resource change reconstruction and fault reconstruction:
in task reconstruction, a baseband resource pool receives a task switching instruction, a task template adapts to an application corresponding to the instruction, a resource pool logic device library calls a reconstruction strategy according to the input of the task template, matches corresponding hardware resources, regenerates a set of resource deployment schemes, a plurality of optional schemes and corresponding evaluation parameters, a user can intervene in selection, and the resource pool loads functional components according to the selection of the deployment schemes. The reconstruction strategy is an open editable script and can be dynamically updated according to needs.
In resource change reconstruction, when the functions or the quantity of software and hardware resources of a baseband resource pool change, the resource pool rearranges a task template or adjusts a resource pool logic equipment library, the resource pool logic equipment library adaptively calls a reconstruction strategy according to input data of the task template, matches corresponding hardware resources, regenerates a set of resource deployment scheme and a plurality of optional schemes, and corresponding evaluation parameters, a user can intervene and select, and the resource pool loads functional components according to the selection of the deployment scheme. The reconstruction strategy is an open editable script and can be dynamically updated according to needs.
In the fault reconstruction, when the baseband resource pool computing resource is in fault, the baseband resource pool logic equipment library adaptively adapts a reconstruction strategy according to input data of a task template, matches corresponding hardware resources, regenerates a set of resource deployment scheme and a plurality of optional schemes and corresponding evaluation parameters, a user can intervene in selection, and the resource pool loads functional components according to the selection of the deployment scheme. The reconstruction strategy is an open editable script and can be dynamically updated according to needs.
The above detailed description of the embodiments of the present invention has been presented in terms of specific embodiments and is intended only to facilitate the understanding of the method and apparatus of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (9)
1. An intelligent deployment and reconstruction method of a baseband resource pool has the following technical characteristics: a plurality of baseband resource pool chassis/board cards are interconnected through optical fibers/Ethernet/cables to form a distributed baseband resource pool processing system for processing multiple computing resources and providing a set of programmable task templates and a set of editable resource pool logic equipment library; the base band resource pool receives the task instruction, adapts the corresponding instruction in the task template, the resource pool logic equipment base matches the corresponding hardware resource according to the input data of the task template, completes the matching of the software and hardware resources, generates a set of resource deployment scheme, a plurality of alternatives and corresponding evaluation parameters, and the deployment scheme can be selected by the user in an intervention way; the resource pool finishes the loading of application function components according to the resource deployment view scheme, realizes the mapping from the platform logic system to the real physical system, and finishes the configuration of the cross-platform baseband resource pool and the intelligent reconstruction and deployment of the baseband resource pool; in the reconstruction and deployment of the baseband resource pool, N =1,2, \8230;, N denotes the chassis number of the baseband resource pool, M =1,2, \8230;, M denotes the identification of different classes of resources, wherein M =1 denotes a DSP type resource, M =2 denotes an FPGA type resource, M =3 denotes a PowerPC type resource, w denotes a FPGA type resource, and nm representing the total number of M classes of resources in the chassis N by using a matrix with dimension of NxM
Representing the total number set of various resources in each chassis by using a matrix with dimension of NxM
Indicates the currentSet of occupation amounts of various types of resources in each chassis of state, wherein d nm D is more than or equal to 0 and represents the occupation amount of m types of resources in the case n nm ≤w nm (ii) a Using matrices of dimension NxM
Representing the occupancy rate set of various resources in each chassis in the current state, wherein nm Indicating the occupancy of the m types of resources in the chassis n,
using vectors P of dimension 1 × M 0 ＝[p 1 p 2 ...p M ]An average value set representing the occupancy rate of various resources in each case at the current state, wherein p m The average value of the occupancy rates of the m-th type resources in each chassis in the current state is shown,
t =1,2,3, \ 8230;, T, T functional components com (1), com (2), com (3), com (4), \8230;, com (T) constitute the application S, each functional component only corresponds to one type of hardware resource, the types and external constraints of the hardware resources corresponding to com (4), \8230;, com (T) are known from the task template, R represents the number of hardware resource deployment schemes capable of bearing the application S, R =1,2,3, \8230, R represents a matrix with dimension R × T in the resource pool logical device library
Represents the case number corresponding to each functional component in each deployment scenario, wherein z rt Represents the number of the machine case corresponding to the component com (t) in the r deployment schemes, and z is more than or equal to 1 rt N is less than or equal to N; using matrices of dimension R x T
Representing cores of functional components in deployment scenarios within their corresponding chassisSlice number in which z rt ' denotes the r arrangement, where the component com (t) is in the cabinet z rt The chip number in (1) is included,
according to the running state of the resource pool, the hardware number Z related to the occupied current hardware resource in the matrix Z' is numbered rt ' delete, delete at the same time z rt ' line of position z r 'and Z' of the correlation matrix Z r Row, to ensure all resources in matrix Z, Z' are in idle state; using a vector Q of dimension 1 × M r ＝[q 1 q 2 ...q M ]Representation based on scheme z r 、z r ' the occupancy rates of various resources in each case after deployment and the root mean square deviation set of the occupancy rates of various resources in the original state in each case are set, wherein q is m Representation is based on scheme z r 、z r ' the occupancy rate of the m-th type resource in each chassis after deployment is deviated from the root mean square of the occupancy rate of the m-th type resource in each chassis in the original state,
wherein l' nm Representation is based on scheme z r 、z r ' occupancy rates for various types of resources in each chassis after deployment,Pm representation is based on scheme z r 、z r The average value of the occupancy rates of the m-th type of resources in each chassis before deployment; defining an evaluation function f = MAX (Q) r ) The return value of the function f is the matrix Q r Maximum value of
Taking any one deployment scheme from the matrixes Z and Z': z is a radical of r 、z r ', calculating: z is a radical of formula r 、z r ' the occupancy rates of various resources in each case after the represented deployment scheme is deployed and the root mean square deviation vector Q of the occupancy rates of various resources in the original state in each case r ＝[q 1 q 2 ...q M ]Is mixing Q with r Carry-in evaluation functionf＝MAX(Q r ) And then taking the deployment scheme from the matrix Z and Z': z is a radical of r+1 、z r+1 ', calculating z r+1 、z r+1 ' the occupancy rates of various resources in each case after the represented deployment scheme is deployed and the root mean square deviation vector Q of the occupancy rates of various resources in the original state in each case r+1 ＝[q 1 q 2 ...q M ]Introduction of Q into r+1 Carry-in evaluation function f r+1 ＝MAX(Q r+1 ) Sequentially traversing all the deployment schemes, and finally obtaining the function f r And the deployment scheme corresponding to the minimum return value is the optimal deployment scheme.
2. The intelligent deployment and reconfiguration method for baseband resource pools according to claim 1, wherein: each baseband resource pool case/board contains various processing resources such as ZYNQ, field programmable gate array FPGA, multi-channel digital signal processing DSP and the like, and the baseband resource pool cases can independently bear function application and can also be matched with each other to complete the realization of functional application.
3. The intelligent deployment and reconfiguration method for baseband resource pools according to claim 1, wherein: when a task and a resource change or a platform fails, the baseband resource pool processing system adaptively adapts a reconstruction strategy, dynamically allocates appropriate resources according to the corresponding reconstruction strategy to complete remapping and reloading of the system, wherein the reconstruction strategy is an open editable script and can be dynamically updated as required.
4. The intelligent deployment and reconfiguration method for baseband resource pools according to claim 3, wherein: the reconstruction strategy comprises a load balance reconstruction strategy based on weighted polling, random, minimum response time, minimum concurrency and Hash algorithm, a machine learning reconstruction strategy based on linear regression, logistic regression, decision tree, random forest, bayes, greedy algorithm and simulated annealing algorithm and other strategies.
5. The intelligent deployment and reconfiguration method for baseband resource pools according to claim 1, wherein: the baseband resource pool case comprises a plurality of signal processing modules and a management control module which are interconnected through a RapidIO bus and an Ethernet, wherein the signal processing modules adopt an interconnection framework based on an analog-digital converter/digital-analog converter AD/DA, a Soc device ZYNQ, a field programmable gate array FPGA and a digital signal processor DSP, and the management control module provides a debugging port, a serial port and a network port for the outside.
6. The intelligent deployment and reconfiguration method for baseband resource pools according to claim 1, wherein: the baseband resource pool reconstruction is divided into three types, namely task reconstruction, resource change reconstruction and fault reconstruction:
in task reconstruction, a baseband resource pool receives a task switching instruction, a task template adapts to an application corresponding to the instruction, a resource pool logic device library calls a reconstruction strategy according to the input of the task template, matches corresponding hardware resources, regenerates a set of resource deployment schemes, a plurality of optional schemes and corresponding evaluation parameters, a user can intervene in selection, and the resource pool loads functional components according to the selection of the deployment schemes.
7. The intelligent deployment and reconfiguration method for baseband resource pools according to claim 6, wherein: in resource change reconstruction, when the functions or the quantity of software and hardware resources of a baseband resource pool change, the resource pool rearranges a task template or adjusts a resource pool logic equipment library, the resource pool logic equipment library adaptively uses a reconstruction strategy according to input data of the task template, matches corresponding hardware resources, regenerates a set of resource deployment scheme and a plurality of optional schemes and corresponding evaluation parameters, a user can intervene and select, and the resource pool loads functional components according to the selection of the deployment scheme.
8. The intelligent deployment and reconfiguration method for baseband resource pools according to claim 3, wherein: the reconstruction strategy is an open editable script and can be dynamically updated according to needs.
9. The intelligent deployment and reconfiguration method for baseband resource pools according to claim 6, wherein: in the fault reconstruction, when the baseband resource pool computing resource is in fault, the baseband resource pool logic equipment library adaptively calls a reconstruction strategy according to input data of a task template, matches corresponding hardware resources, regenerates a set of resource deployment schemes, a plurality of optional schemes and corresponding evaluation parameters, and a user can intervene in selection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910810868.0A CN110430591B (en) | 2019-08-30 | 2019-08-30 | Intelligent deployment and reconstruction method for baseband resource pool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910810868.0A CN110430591B (en) | 2019-08-30 | 2019-08-30 | Intelligent deployment and reconstruction method for baseband resource pool |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110430591A CN110430591A (en) | 2019-11-08 |
| CN110430591B true CN110430591B (en) | 2022-10-14 |
Family
ID=68416625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910810868.0A Active CN110430591B (en) | 2019-08-30 | 2019-08-30 | Intelligent deployment and reconstruction method for baseband resource pool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110430591B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112711560B (en) * | 2021-02-10 | 2023-05-26 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Reconstruction method for single-point connection of ZYNQ chip to rapidIO bus |
| CN114760172B (en) * | 2022-04-13 | 2024-04-19 | 北京博识广联科技有限公司 | Method and device for identifying radio frequency baseband comprehensive characteristic signals |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101854663A (en) * | 2010-04-30 | 2010-10-06 | 华为技术有限公司 | Data transmission equipment and method and communication system |
| CN107135018A (en) * | 2012-10-10 | 2017-09-05 | 华为技术有限公司 | The method and array system communicated by distributed aerial array system |
| CN103841647B (en) * | 2014-03-07 | 2017-04-12 | 北京邮电大学 | Multi-granularity telescopic packaging device and method based on base station resource pool |
| CN104270777B (en) * | 2014-09-18 | 2017-09-08 | 北京邮电大学 | The performance statistics appraisal procedure of base station resource pond physical layer algorithm encapsulation scheme |
| CN105844020A (en) * | 2016-03-23 | 2016-08-10 | 中国电子科技集团公司第十研究所 | Abstract integration design method of complex electronic system |
| CN106533457B (en) * | 2016-11-29 | 2019-04-05 | 中国运载火箭技术研究院 | A kind of integrated wireless communication system and its implementation |
-
2019
- 2019-08-30 CN CN201910810868.0A patent/CN110430591B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110430591A (en) | 2019-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110162388A (en) | A kind of method for scheduling task, system and terminal device | |
| US20160196488A1 (en) | Neural network computing device, system and method | |
| CN110430591B (en) | Intelligent deployment and reconstruction method for baseband resource pool | |
| CN103763346B (en) | A kind of distributed resource scheduling method and device | |
| CN111831359B (en) | Weight precision configuration method, device, equipment and storage medium | |
| CN111831355B (en) | Weight precision configuration method, device, equipment and storage medium | |
| CN102541655A (en) | Method and device for implementing dynamic load balancing | |
| CN112527513A (en) | Method and system for dynamically distributing multiple GPUs | |
| CN111371616A (en) | Virtual network function chain deployment method and system for NUMA (non Uniform memory Access) architecture server | |
| CN114443284A (en) | Cluster resource load balancing method and device, electronic equipment and medium | |
| US20240119329A1 (en) | Quantum computer operating system, quantum computer and readable storage medium | |
| CN102929693B (en) | Performance evaluation method and device for servers of whole equipment cabinet | |
| KR100367715B1 (en) | Digital hopfield neural network chip for channel assignment in cellular mobile communication | |
| CN114217944A (en) | Dynamic load balancing method for neural network aiming at model parallelism | |
| CN116701001B (en) | Target task allocation method and device, electronic equipment and storage medium | |
| CN116523045B (en) | Deep learning reasoning simulator oriented to multi-core chip | |
| CN116954815A (en) | Resource scheduling method and device, computer equipment and computer readable storage medium | |
| CN111722923A (en) | Heterogeneous resource calling method and device and computer readable storage medium | |
| CN113791863B (en) | Virtual container-based power Internet of things proxy resource scheduling method and related equipment | |
| CN115550373A (en) | Combined test task environment load balancing modeling method based on cloud platform management and control | |
| CN113795032B (en) | Method and device for judging invisible faults of indoor division, storage medium and equipment | |
| CN112637032B (en) | Service function chain deployment method and device | |
| EP3832470A1 (en) | High bandwidth memory system with dynamically programmable distribution scheme | |
| US20210319295A1 (en) | Data processing module, data processing system and data processing method | |
| CN112102305A (en) | Multi-skeleton development grade detection method and terminal equipment |
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 |