CN109636134B - Resource management architecture for distributed avionics system - Google Patents
Resource management architecture for distributed avionics system Download PDFInfo
- Publication number
- CN109636134B CN109636134B CN201811392737.7A CN201811392737A CN109636134B CN 109636134 B CN109636134 B CN 109636134B CN 201811392737 A CN201811392737 A CN 201811392737A CN 109636134 B CN109636134 B CN 109636134B
- Authority
- CN
- China
- Prior art keywords
- domain
- resource
- local
- resource manager
- resource management
- 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
- 238000005192 partition Methods 0.000 claims abstract description 22
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 5
- 230000008520 organization Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G06Q50/40—
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention belongs to the field of comprehensive modularized avionics system design, and relates to a resource management architecture for a distributed avionics system; the architecture of the present invention divides a distributed avionics system into five different domains: a system domain, a cluster domain, a node domain, a virtualization layer domain, and a partition to perform resource management; a global resource manager is configured in a system domain, and local resource managers are respectively configured in other four domains; the global resource manager controls the resources in the system domain and corresponds to the highest layer of the resource management component hierarchy; the local resource manager block is used for supervising and controlling resources in the corresponding domains; and is responsible for communicating with its local resource manager in the other domain at the same level or one level lower; according to the invention, the multi-domain division of the distributed avionics system architecture and the hierarchical resource monitoring and management organization architecture are adopted, so that the running resource management of the whole avionics system is realized, and the global resource management and fault tolerance control capability of the system is effectively improved.
Description
Technical Field
The invention belongs to the field of comprehensive modularized avionics system design, and particularly relates to a resource management architecture for a distributed avionics system.
Background
The comprehensive modularized avionics system (Integrated Module Avionics, IMA) achieves high integration of software and hardware, and centralized control of the whole aircraft is achieved through a high-speed bus network, so that the weight of the aircraft is effectively reduced, and the comprehensive modularized avionics system is widely applied to civil aircraft. As an onboard safety critical system, a time and space isolation mechanism defined in the ARINC 653 standard is commonly adopted in the IMA design to realize partitioning, and each application is operated by a two-stage scheduling mode. The time and space isolation mechanism effectively avoids the mutual influence of applications with different security levels, thereby improving the overall reliability and security of IMA.
Disclosure of Invention
The purpose of the invention is that: a resource management architecture for a distributed avionics system is provided, which is used for realizing hierarchical monitoring and management of system resources under the architecture of the distributed and cloud-like avionics system.
In order to solve the technical problem, the technical scheme of the invention is as follows:
a resource management architecture for a distributed avionics system, the resource management architecture dividing the distributed avionics system into five different domains: a system domain, a cluster domain, a node domain, a virtualization layer domain, and a partition to perform resource management;
the system domain is a resource management domain containing the whole distributed comprehensive modularized avionics system;
the cluster domain is a resource domain related to a node cluster formed by aggregation of a plurality of common processing modules of the same or different types and related networks;
the node domain is a resource domain which comprises a single universal module and is related to software running on the single universal module;
the virtualization layer domain comprises a resource domain necessary for supporting each partition operating system running on a single node domain;
the subareas comprise resource domains related to application software running on a virtualization layer, namely each subarea operating system;
a global resource manager is configured in a system domain, and local resource managers are respectively configured in other four domains; the global resource manager controls resources in the system domain, corresponding to the highest level of the resource management component hierarchy; the local resource manager block is used for supervising and controlling the resources in the corresponding domain and is responsible for communicating with the local resource manager in other domains of the same layer or one layer lower.
The global resource manager is used for providing global resource management service, monitoring and controlling the local resource manager of each domain and giving out global resource management decisions.
The local resource manager in the cluster domain is used for supervising and controlling the local resource manager in the node domain, the local resource of the off-chip gateway and the local resource of the off-chip switch.
The local resource manager in the node domain is used for supervising and controlling the virtualized layer and other non-virtualized resources in the computing node, and comprises a network interface, a storage gateway or an on-chip memory, an input-output component and local resources of the off-chip/on-chip gateway.
The local resource manager in the virtualization layer domain is used for supervising and controlling local resources in the virtualization layer domain, including local resources of partitions, network interfaces and application components.
The local resource manager of the subarea is used for supervising and controlling the local running resource of the application software in the subarea.
The beneficial effects of the invention are as follows:
the invention combines the characteristics of the distributed avionics system architecture, realizes the management of the resources of the whole avionics system in the running process by dividing the system architecture into multiple domains and adopting a hierarchical resource monitoring and management organization architecture, provides resource sensing and scheduling services for system management and fault tolerance control, and particularly provides support for dynamic reconfiguration of the avionics system. The invention can effectively improve the global resource management and control and fault tolerance control capability of the system.
Drawings
FIG. 1 is a schematic view of a resource management domain hierarchy of the present invention;
FIG. 2 is a schematic diagram of a resource management architecture of the present invention;
FIG. 3 is a schematic diagram of a resource management service of the present invention;
wherein, LRM-local resource manager, GRM-global resource manager.
Detailed Description
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
the invention provides a resource management architecture for a distributed avionics system, which realizes the resource perception and multi-level management of the whole avionics architecture through a global-local distributed management organization form and mainly comprises a multi-domain division and hierarchy management architecture for the resource management of the distributed avionics system and a resource management service group design.
1. Resource management domain partitioning
According to the hierarchy of establishing a resource management architecture on a distributed integrated modularized avionics system platform, the invention adopts the concept of resource management domains, as shown in fig. 1, and considers 5 different domains in combination with the characteristics of the distributed avionics system platform to execute resource management: system domain, cluster domain, node domain, virtualization layer domain, partition domain, domain representing system composition from resource management perspective.
The system domain comprises a resource management domain of the whole distributed comprehensive modularized avionics system.
The cluster domain comprises resource domains related to a node cluster formed by aggregation of a plurality of common processing modules of the same or different types and related networks.
The node domain represents the resource domain involved in a single generic module and the software running on it.
The virtualization layer domain is the resource domain necessary to support each partition operating system running on a single node domain.
The partition is a resource domain related to the application software running on the virtualization layer, i.e. each partition operating system, and provides resource support for the execution of the application software.
2. Resource management architecture
On the basis of defining 5 kinds of resource management domain division, the invention describes a general hierarchical resource management architecture which is flexible enough to adapt to heterogeneous resources of a distributed avionics system platform, namely, by configuring a global resource manager in a system domain; and respectively configuring local resource managers in other four domains to realize hierarchical resource management of the distributed comprehensive modularized avionics system. In addition, a local resource monitor and a local resource manager are configured in each local resource management domain, so that the monitoring and control of resource entities in each domain are realized respectively. The class 4 manager function of the present invention is described as follows:
global resource manager
A global resource management service is provided. Information received from the various local resource managers gives a global resource management decision.
Local resource manager
Providing a local domain resource management service includes sending abstract state information of a resource to a global resource manager, accepting a reconfiguration command from the global resource manager, adapting the global resource management command to local resource scheduling parameters, initializing local reconfiguration, and the like.
Local resource monitor
Monitoring services (i.e., monitoring availability, energy and detecting errors, etc.) are provided.
Local resource scheduler
Providing dispatch services and configuration services. Dispatch services such as time triggered message distribution, task scheduling according to offline/online scheduling parameters, etc. The configuration service accepts a configuration request, updates configuration, etc. for the current domain operation at the upper level.
The system resource management architecture and various levels of resource management capabilities are shown in fig. 2. The global resource manager controls resources in the overall system domain, corresponding to the highest level of the resource management hierarchy. For each of the other domains, there is a local resource manager for policing and controlling resources in the corresponding domain. The high-level resource manager interacts with a lower-level local resource manager or directly with the monitor of the individual resource itself and the local resource scheduler.
The local resource manager in the cluster domain is responsible for supervising and controlling the local resource manager in the node domain, the local resources of the off-chip gateway, and the local resources of the off-chip switch.
The local resource manager in the node domain is responsible for supervising and controlling the virtualized layer and other non-virtualized resources in the compute node, including network interfaces, storage gateways or on-chip memory, input-output components, and local resources of off-chip/on-chip gateways.
The local resource manager of the virtualization layer domain is responsible for policing and controlling local resources in the virtualization layer domain, including partitions, network interfaces, and local resources of application components.
The local resource manager of the partition is responsible for supervising and controlling the locally running resources of the application software within the partition.
3. Resource management service design
As shown in fig. 3, the present invention configures different services for functions of each hierarchy (global resource manager and local resource manager) based on the foregoing resource management architecture and each domain resource manager function, and provides a typical generic service list for different resource management domains, which is described in detail as follows:
1) Global resource management service group
(1) Collecting state information from a local resource manager
The global resource manager gathers all the information monitored by the local resource manager with which it is cross-linked, the main parameters including the physical name of the resource and the monitored variables.
(2) Acquisition configuration
The global resource manager is responsible for all offline configuration databases or calculates a new configuration (new schedule or schedule parameters) at run-time.
(3) Global reconfiguration
The global resource manager will make reconfiguration decisions based on system level information analysis and monitoring, taking into account system level constraints, to adapt the system to different modes or states.
(4) Sending commands to a local resource manager
Once the reconfiguration decisions are taken, the global resource manager will communicate with all reconfiguration related resource local resource managers through the network and middleware.
(5) Managing external inputs
The external input includes the real-time resource status uploaded to the global manager by each local resource manager, which may constitute a new constraint on the system, and the global resource manager computes new configurations satisfying the constraint and then transmits them to each local resource manager.
2) Local resource management service group
(1) Universal local resource management service
(a) Receiving/reading monitoring information from a monitor
The resource monitor sends information to the local resource manager in a communication mode such as interrupt and polling.
(b) Computing an abstract state level
Based on the monitoring information, the local resource manager is responsible for calculating the abstraction level of the resource state variables, including energy, availability, reliability, behavior, etc., to reduce the overhead of transmitting low-level monitoring variables.
(c) Transmitting information to global resource manager/local resource manager
Each local resource manager will communicate the abstract state of the domain resource it is in to the local resource manager of the previous level through the network and middleware.
(d) Receiving commands from a global resource manager/local resource manager
The local resource manager can only receive commands from other local resource managers or from the global resource manager.
(e) Local policy for translating commands into local resource schedulers
The local resource manager, upon receiving a command from the global resource manager, maps it to the scheduling policy of the local resource scheduler.
(f) Configuring a local resource scheduler
The local resource manager configures the local resource scheduler in the domain in which it resides and sends commands to the lower level local resource manager.
(g) Triggering local reconfiguration
The local resource state changes may be localized by a local resource manager in the domain. For example, a certain low criticality partition is stopped, after which the local resource manager should report the new state of the resource to the global resource manager to maintain the correlation of the overall system state.
(2) Local resource management services in cluster domains
The local resource manager in the cluster domain serves as a granularity interface between the global resource manager and the different types of computing nodes, and no separate resource processing is performed, and only the local resource manager in the lower domain, namely the local resource manager in the node domain, is configured and monitored. The local resource manager in the cluster domain has the following specific services:
(a) Monitoring a low-level local resource manager
The monitoring information collected by the lower level local resource manager, i.e. the node domain resource manager, is received or read.
(b) Configuring a low-level local resource manager
Instructions and commands received from the global resource manager or higher level local resource manager configure the functions and modes of the lower level local resource manager.
(3) Local resource management services in a node domain
The local resource manager in the node domain must handle the resource information of the virtualized layer domain and the individual resources, such as gateways or non-virtualized storage gateways. The local resource manager in the node domain has the following specific services:
(a) Configuring a low-level local resource manager
The monitoring information collected by the lower level local resource manager, i.e., the virtualization layer domain, is received or read.
(b) Configuring a low-level local resource manager
Instructions and commands are received for a higher level local resource manager or global resource manager to configure the functions and modes of a lower level local resource manager.
(4) Local resource manager services in a virtualization layer domain
The local resource manager in the virtualization layer domain may implement system configuration (perform a reset, stop another partition), modify the runtime scheduling plan, etc. The local resource manager in the virtualization layer domain has the following specific services.
(a) Configuring a low-level local resource manager
The monitoring information collected by the low-level local resource manager, i.e., the regional resource manager, is received or read.
(b) Configuring a low-level local resource manager
Instructions and commands are received for a higher level local resource manager or global resource manager to configure the functions and modes of a lower level local resource manager.
(5) Local resource manager services in a partition
The local resource manager in the partition comprises an internal scheduler of the partition operating system, so that the application scheduling parameters are configured, and the local resource manager in the partition has monitoring capability, and allows the local resource manager in the partition to collect the health states of the partition operating system and each application.
Claims (4)
1. The resource management architecture for the distributed avionics system is characterized in that: the resource management architecture divides the distributed avionics system into five different domains: a system domain, a cluster domain, a node domain, a virtualization layer domain, and a partition to perform resource management;
the system domain is a resource management domain containing the whole distributed comprehensive modularized avionics system;
the cluster domain is a resource domain related to a node cluster formed by aggregation of a plurality of common processing modules of the same or different types and related networks;
the node domain is a resource domain which comprises a single universal module and is related to software running on the single universal module; the local resource manager in the node domain is used for supervising and controlling the virtualized layer and other non-virtualized resources in the computing node, and comprises a network interface, a storage gateway or an on-chip memory, an input/output component and local resources of an off-chip/on-chip gateway;
the virtualization layer domain comprises a resource domain necessary for supporting each partition operating system running on a single node domain; the local resource manager in the virtualization layer domain is used for supervising and controlling local resources in the virtualization layer domain, including local resources of partitions, network interfaces and application components;
the subareas comprise resource domains related to application software running on a virtualization layer, namely each subarea operating system;
a global resource manager is configured in a system domain, and local resource managers are respectively configured in a cluster domain, a node domain, a virtualization layer domain and a sub-region; the global resource manager controls resources in the system domain, corresponding to the highest level of the resource management component hierarchy; the local resource manager is used for supervising and controlling the resources in the corresponding domain and is responsible for communicating with the local resource manager in other domains of the same layer or one layer lower.
2. The distributed avionics system oriented resource management architecture of claim 1, wherein: the global resource manager is used for providing global resource management service, monitoring and controlling the local resource manager of each domain and giving out global resource management decisions.
3. The distributed avionics system oriented resource management architecture of claim 1, wherein: the local resource manager in the cluster domain is used for supervising and controlling the local resource manager in the node domain, the local resource of the off-chip gateway and the local resource of the off-chip switch.
4. The distributed avionics system oriented resource management architecture of claim 1, wherein: the local resource manager of the subarea is used for supervising and controlling the local running resource of the application software in the subarea.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811392737.7A CN109636134B (en) | 2018-11-21 | 2018-11-21 | Resource management architecture for distributed avionics system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811392737.7A CN109636134B (en) | 2018-11-21 | 2018-11-21 | Resource management architecture for distributed avionics system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109636134A CN109636134A (en) | 2019-04-16 |
| CN109636134B true CN109636134B (en) | 2023-06-13 |
Family
ID=66068595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811392737.7A Active CN109636134B (en) | 2018-11-21 | 2018-11-21 | Resource management architecture for distributed avionics system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636134B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4154111A4 (en) * | 2020-09-01 | 2023-04-12 | Huawei Cloud Computing Technologies Co., Ltd. | Systems and methods of hybrid centralized distributive scheduling on shared physical hosts |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102916778A (en) * | 2012-10-24 | 2013-02-06 | 四川九洲空管科技有限责任公司 | Signal processing method and system for airborne equipment |
| CN105786494A (en) * | 2016-02-24 | 2016-07-20 | 中国航空工业集团公司沈阳飞机设计研究所 | Software configuration information data management system |
| CN107943459A (en) * | 2017-11-20 | 2018-04-20 | 中国运载火箭技术研究院 | A kind of generalization spacecraft Integrated Electronic System |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050132121A1 (en) * | 2003-12-16 | 2005-06-16 | Wind River Systems, Inc. | Partitioned operating system tool |
| FR2934693B1 (en) * | 2008-07-30 | 2011-03-25 | Airbus France | A DYNAMIC RECONFIGURATION ONBOARD AERONAUTICAL SYSTEM, ASSOCIATED METHOD AND AIRCRAFT EMBARKING SUCH A SYSTEM. |
| CN103680215B (en) * | 2013-12-04 | 2016-04-06 | 海丰通航科技有限公司 | Low-altitude aviation service station |
| CN104008452A (en) * | 2014-05-29 | 2014-08-27 | 中国航空无线电电子研究所 | Fault-tolerant management system and method for avionics core system |
| US10229372B2 (en) * | 2015-05-15 | 2019-03-12 | Taleris Global Llp | Method for rescheduling flights affected by a disruption and an airline operations control system and controller |
| CN105844556A (en) * | 2016-05-18 | 2016-08-10 | 四川航天系统工程研究所 | Intelligent tourism system based on Beidou |
-
2018
- 2018-11-21 CN CN201811392737.7A patent/CN109636134B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102916778A (en) * | 2012-10-24 | 2013-02-06 | 四川九洲空管科技有限责任公司 | Signal processing method and system for airborne equipment |
| CN105786494A (en) * | 2016-02-24 | 2016-07-20 | 中国航空工业集团公司沈阳飞机设计研究所 | Software configuration information data management system |
| CN107943459A (en) * | 2017-11-20 | 2018-04-20 | 中国运载火箭技术研究院 | A kind of generalization spacecraft Integrated Electronic System |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109636134A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Obermaisser | Event-triggered and time-triggered control paradigms | |
| CN108092813A (en) | Data center's total management system server hardware Governance framework and implementation method | |
| CN107615792B (en) | Management method and system for MTC event | |
| US20070294736A1 (en) | Method for dynamic information technology infrastructure provisioning | |
| Dubey et al. | A software platform for fractionated spacecraft | |
| CN103973815A (en) | Method for unified monitoring of storage environment across data centers | |
| US20100100286A1 (en) | On-board aeronautical system with dynamic reconfiguration, associated method and aircraft carrying such a system | |
| Obermaisser et al. | Architectures for mixed-criticality systems based on networked multi-core chips | |
| Durrieu et al. | DREAMS about reconfiguration and adaptation in avionics | |
| Lee et al. | Scheduling tool and algorithm for integrated modular avionics systems | |
| Gala et al. | RT-cloud: Virtualization technologies and cloud computing for railway use-case | |
| Weiss et al. | Fail-operational automotive software design using agent-based graceful degradation | |
| CN109636134B (en) | Resource management architecture for distributed avionics system | |
| US20070174437A1 (en) | Method for managing and monitoring the operation of a plurality of distributed hardware and/or software systems that are integrated into at least one communications network, and system for carrying out the method | |
| Kopetz et al. | In-vehicle real-time fog computing | |
| Zhou et al. | An AADL-based design for dynamic reconfiguration of DIMA | |
| Obermaisser et al. | DECOS: an integrated time-triggered architecture | |
| Singh et al. | Event handling for distributed real-time cyber-physical systems | |
| Kumar et al. | imanage: Policy-driven self-management for enterprise-scale systems | |
| Aldegheri et al. | A containerized ROS-compliant verification environment for robotic systems | |
| Dhiah el Diehn et al. | Incremental, distributed, and concurrent service coordination for reliable and deterministic systems-of-systems | |
| Huber et al. | A resource management framework for mixed-criticality embedded systems | |
| CN110955602A (en) | Distributed embedded software testing system based on resource sharing | |
| CN103078764A (en) | Operational monitoring system and method based on virtual computing task | |
| Pradhan et al. | Towards a generic computation model for smart city platforms |
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 |