CN112929448A - Dynamic scheduling model in DDS-based multipath transmission scene - Google Patents
Dynamic scheduling model in DDS-based multipath transmission scene Download PDFInfo
- Publication number
- CN112929448A CN112929448A CN202110262037.1A CN202110262037A CN112929448A CN 112929448 A CN112929448 A CN 112929448A CN 202110262037 A CN202110262037 A CN 202110262037A CN 112929448 A CN112929448 A CN 112929448A
- Authority
- CN
- China
- Prior art keywords
- data
- scheduling
- certainty
- dds
- subscriber
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
- H04L43/0829—Packet loss
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/80—Actions related to the user profile or the type of traffic
- H04L47/805—QOS or priority aware
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to a dynamic scheduling model under a DDS-based multipath transmission scene, belonging to the field of communication electronic computers. The model comprises a plurality of application programs, wherein at least one application program in the application programs is provided with a subscriber; a publisher in the application receives data; the publisher processes and sends data to the subscriber; the application programs are all provided with a scheduling client, and the scheduling client interacts with a scheduling management server; scheduling the client to interact with a publisher/subscriber in the corresponding application program; the scheduling client is responsible for reporting data certainty/time certainty evaluation data to the scheduling management server; and the dynamic scheduling model operates according to one of a load sharing mode, a static mode and a preferred mode according to the data certainty/time certainty evaluation result. The invention provides a multipath transmission scheduling mechanism based on time certainty and data certainty evaluation results under a data distribution service scene, so that scheduling management has dynamic property and real-time property.
Description
Technical Field
The invention relates to a dynamic scheduling model under a DDS-based multipath transmission scene, belonging to the field of communication electronic computers.
Background
Dds (data Distribution service), which is a data Distribution service, is a data publishing and subscribing standard specially designed for a real-time system and formally published by an Object Management Group (OMG). The DDS specification describes a data-centric publish-subscribe (DCPS) model for distributed application communication and integration. The specification defines application program interfaces (api) and communication semantics (behavior and quality of service) that enable information producers to efficiently deliver information to matching consumers. The data distribution service and the related interoperation specification provide standard interfaces and behaviors, realize high portability of application programs, and simultaneously ensure the scalability, flexibility and robustness of the whole system.
Data Distribution Services (DDS) rely on the use of QoS. QoS (quality of service) is a set of characteristics that control DDS service behavior. QoS consists of QoS policies that are separate from each other. The DDS provides QoS policies for applications to control a large number of non-functional application attributes such as data availability, data delivery, data timeliness, and resource usage. The semantics and behavior of DDS entities, such as topics, data readers, and data writers, can be controlled by available QoS policies. These policy controls and end-to-end properties are considered part of the subscription match.
The DDS specification supports multiple Data senders (Data writers) writing the same Data object instance at the same time. And a part of the QoS strategy defined by the QoS strategy can be used for controlling the matching behavior of a Data Reader (Data Reader). For example, owership specifies whether multiple data senders are allowed to update the same data object instance; OWNERSHIP STRENGTH specifies how to select data instance updates for a unique data sender in EXCLUSIVE mode; the DESTINATION ORDER specifies how to select a unique final data instance value if STRENGTH is the same; LIVELINESS provide for keep-alive detection of topological connections, and provide a handoff mechanism for redundant systems based on EXCLUSE mode, and the like.
For the combination and application of the above QoS policies, we can implement DDS based multiplex scheduling. However, such scheduling relies on fixed parameter QoS policy configuration, such as a preconfigured keep-alive detection interval (LIVELINESS Leased Duration). In an actual data distribution service scenario, we may face a transient network state, an end-to-end uncertainty, and the like, and scheduling based on a fixed Qos policy does not have adaptability and flexibility.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: a multi-path transmission scheduling mechanism based on time certainty and data certainty evaluation results realizes dynamic and sensitive scheduling in a data distribution service scene.
In order to solve the technical problems, the technical scheme provided by the invention is as follows: a dynamic scheduling model based on DDS under a multipath transmission scene comprises a plurality of application programs, wherein at least one application program in the application programs is provided with a subscriber; a publisher in the application program receives data sent by a data source; the publisher processes and sends data to the subscriber; the application programs are all provided with a scheduling client, and the scheduling client is interacted with a scheduling management server; the scheduling client interacts with a publisher/subscriber in a corresponding application program;
the scheduling client is responsible for reporting DDS entity information and data certainty/time certainty evaluation data to a scheduling management server; the scheduling management server side issues Qos strategy configuration to each client side; the scheduling management client has the capability of collecting time certainty/data certainty evaluation data and also has the capability of executing QoS strategy configuration on the DDS entity. The scheduling management server provides a configuration interface for a user, is responsible for global scheduling work, and converts a scheduling instruction into specific QoS strategy configuration;
the data certainty/time certainty evaluation data comprises one-way time delay from a data transmitter of a publisher to a data reader of a subscriber, one-way jitter from the data transmitter of the publisher to the data reader of the subscriber, round-trip time delay from the data transmitter of the publisher and the data reader of the subscriber, round-trip jitter from the data transmitter of the publisher and the data reader of the subscriber, and packet loss rate from the data transmitter of the publisher to the data reader of the subscriber; and setting one or more threshold conditions according to the data certainty/time certainty evaluation data to control the on-off of the transmission path in a multipath scene, so as to realize that the dynamic scheduling model operates according to one mode of a load sharing mode, a static mode and a preferred mode.
The further improvement of the scheme is as follows: in the load sharing mode, each transmission path is in an equally effective state,
the further improvement of the scheme is as follows: in the load sharing mode, the transmission path higher than the threshold condition exits the load sharing group until the transmission path rejoins the load sharing group after being lower than the threshold condition.
The further improvement of the scheme is as follows: in the static mode, the state of each transmission path is determined according to the priority.
The further improvement of the scheme is as follows: in the static mode, only when the priority of a certain transmission path is the highest currently and the evaluation result does not exceed the set threshold, the transmission path is in an effective state.
The further improvement of the scheme is as follows: and under the preferential mode, selecting the most suitable transmission path as an effective transmission path according to the data certainty/time certainty evaluation and evaluation result of the transmission path.
The further improvement of the scheme is as follows: in the preferred mode, one of the following preferences is selected, 1) unidirectional time delay is preferred; 2) one-way jitter is prior; 3) round-trip delay is prior; 4) round-trip jitter is prior; 5) the packet sending rate takes precedence.
The invention has the beneficial effects that: the invention provides a multiplex transmission scheduling mechanism based on time certainty and data certainty evaluation results in a data distribution service scene, and the multiplex transmission scheduling mechanism is used as a switching or filtering condition to enable scheduling management to have dynamic property and real-time property. And the method is selected in three scheduling modes, and covers most application scenes of multi-path transmission.
Detailed Description
Examples
The dynamic scheduling model in the DDS-based multipath transmission scenario of this embodiment includes a plurality of application programs, where at least one of the application programs has a subscriber; a publisher in the application program receives data sent by a data source; the publisher processes and sends data to the subscriber; the application programs are all provided with a scheduling client, and the scheduling client is interacted with a scheduling management server; the scheduling client interacts with a publisher/subscriber in a corresponding application program;
the scheduling client is responsible for reporting DDS entity information and data certainty/time certainty evaluation data to a scheduling management server; the scheduling management server side issues Qos strategy configuration to each client side; the scheduling management client has the capability of collecting time certainty/data certainty evaluation data and also has the capability of executing QoS strategy configuration on the DDS entity. The scheduling management server provides a configuration interface for a user, is responsible for global scheduling work, and converts a scheduling instruction into specific QoS strategy configuration;
the data certainty/time certainty evaluation data comprises one-way time delay from a data transmitter of a publisher to a data reader of a subscriber, one-way jitter from the data transmitter of the publisher to the data reader of the subscriber, round-trip time delay from the data transmitter of the publisher and the data reader of the subscriber, round-trip jitter from the data transmitter of the publisher and the data reader of the subscriber, and packet loss rate from the data transmitter of the publisher to the data reader of the subscriber; and setting one or more threshold conditions according to the data certainty/time certainty evaluation data to control the on-off of the transmission path in a multipath scene, so as to realize that the dynamic scheduling model operates according to one mode of a load sharing mode, a static mode and a preferred mode.
It should be noted that when several different threshold conditions are set, if the evaluation result of any type of configured threshold value in the current transmission path exceeds the set threshold value, no matter whether the current transmission path is in an effective state, the selection range of the current transmission mode needs to be exited, and other transmission paths take over preferentially.
In the load sharing mode of this embodiment, each transmission path is in an equally effective state,
in the load sharing mode of this embodiment, the transmission path higher than the threshold condition exits from the load sharing group until the transmission path rejoins the load sharing group after being lower than the threshold condition.
In the load sharing mode of this embodiment, the ownerhip QoS of all data transmitters is set to the SHARED mode. I.e. the data reader will read and process all valid data transmitters simultaneously. When the scheduling management mechanism finds that the evaluation result of a certain transmission path exceeds the set threshold, the scheduling management mechanism immediately informs the data transmitter of the path to stop the transmission behavior, and resumes the transmission behavior of the data transmitter after the evaluation result is lower than the set threshold.
In the static mode of this embodiment, the state of each transmission path is determined according to the priority.
In the static mode of this embodiment, only when the priority of a certain transmission path is currently the highest and the evaluation result does not exceed the set threshold, the transmission path is in the valid state.
The ownerhip QoS of all data transmitters of the present embodiment is set to the SHARED mode. I.e. the data reader will read and process the data of all active data transmitters simultaneously. The scheduling management mechanism determines the effective path according to the priority configuration of each transmission path. Defaulting the path without configured priority to be the lowest priority; the plurality of highest priority paths will be set to the active state simultaneously. The schedule management mechanism will inform the data transmitters of other paths in the invalid state to stop transmitting until the path is switched to the valid state.
In the preferred mode of this embodiment, a most suitable one is selected as an effective transmission path according to the evaluation result of data certainty/time certainty of the transmission path.
In the preferred mode of this embodiment, one of the following preferences, 1) one-way delay preference, will be selected; 2) one-way jitter is prior; 3) round-trip delay is prior; 4) round-trip jitter is prior; 5) the packet sending rate takes precedence.
In the preferred mode of the embodiment, ownerhip QoS of all data transmitters is set to the EXCLUSIVE mode, all data transmitting devices are in a transmitting state, but a data reader can only read and process data transmitted by one of the data transmitters at the same time. Taking one-way time delay priority as an example, the scheduling management mechanism counts and compares the one-way time delay information of all paths in real time, selects a path with the lowest current one-way time delay as an effective path, and is realized by adjusting OWNERSHIP STRENGTH of a data transmitter of the scheduling management mechanism. Meanwhile, the switching process of the effective path is realized by adjusting OWNERSHIP STRENGTH.
Like the load sharing mode and the static mode, when the evaluation result of a certain transmission path exceeds the set threshold, the transmission path is disabled and exits from the selected group, and after the evaluation result is lower than the set threshold, the transmission path is recovered to be effective and rejoins the selected group.
The time certainty and data certainty evaluation of the embodiment can be obtained through modification based on a real-time publish-subscribe protocol stack, or through other three-party network quality detection tools. The present embodiment provides a plurality of scheduling modes using the case where the evaluation results of the time certainty and the data certainty are determined.
In this embodiment, when the scheduling management mechanism finds that all paths fail due to the evaluation result exceeding the threshold, the scheduling management mechanism ensures normal operation of at least one transmission path, that is, specifies validity of one or more transmission paths as a bottom entry mechanism. And when the evaluation result of one or more paths is restored to be lower than the threshold value, the bottom-trapping mechanism is ended. Since the scheduling management mechanism uses the real-time certainty and data certainty evaluation result as the standard for filtering or switching, we need to consider the scheduling management oscillation that may be brought by the real-time change of the evaluation result, which causes frequent switching and brings unnecessary performance overhead and network overhead to the whole system. Thereby improving the robustness of the entire model. In addition, there are two ways to suppress oscillations: 1. setting a reasonable service processing interval and time delay; 2. an exponential back-off mechanism is used.
The present invention is not limited to the specific technical solutions of the above embodiments, and other embodiments of the present invention are possible in addition to the above embodiments. It will be understood by those skilled in the art that various changes, substitutions of equivalents, and alterations can be made without departing from the spirit and scope of the invention.
Claims (6)
1. A dynamic scheduling model based on DDS under a multipath transmission scene comprises a plurality of application programs and is characterized in that: at least one of the application programs has a subscriber; a publisher in the application program receives data sent by a data source; the publisher processes and sends data to the subscriber; the application programs are all provided with a scheduling client, and the scheduling client is interacted with a scheduling management server; the scheduling client interacts with a publisher/subscriber in a corresponding application program;
the scheduling client is responsible for reporting DDS entity information and data certainty/time certainty evaluation data to a scheduling management server; the scheduling management server side issues Qos strategy configuration to each client side; the scheduling management client has the capability of collecting time certainty/data certainty evaluation data and also has the capability of executing QoS strategy configuration on the DDS entity;
the scheduling management server provides a configuration interface for a user, is responsible for global scheduling work, and converts a scheduling instruction into specific QoS strategy configuration;
the data certainty/time certainty evaluation data comprises one-way time delay from a data transmitter of a publisher to a data reader of a subscriber, one-way jitter from the data transmitter of the publisher to the data reader of the subscriber, round-trip time delay from the data transmitter of the publisher and the data reader of the subscriber, round-trip jitter from the data transmitter of the publisher and the data reader of the subscriber, and packet loss rate from the data transmitter of the publisher to the data reader of the subscriber; and setting one or more threshold conditions according to the data certainty/time certainty evaluation data to control the on-off of the transmission path in a multipath scene, so as to realize that the dynamic scheduling model operates according to one mode of a load sharing mode, a static mode and a preferred mode.
2. The dynamic scheduling model in the DDS-based multipath transmission scenario as claimed in claim 1, wherein: in the load sharing mode, each transmission path is in an equally effective state,
the dynamic scheduling model in the DDS-based multiplexing scenario as claimed in claim 2, wherein: in the load sharing mode, the transmission path higher than the threshold condition exits the load sharing group until the transmission path rejoins the load sharing group after being lower than the threshold condition.
3. The dynamic scheduling model in the DDS-based multipath transmission scenario as claimed in claim 1, wherein: in the static mode, the state of each transmission path is determined according to the priority.
4. The dynamic scheduling model in the DDS-based multipath transmission scenario as claimed in claim 3, wherein: in the static mode, only when the priority of a certain transmission path is the highest currently and the evaluation result does not exceed the set threshold, the transmission path is in an effective state.
5. The dynamic scheduling model in the DDS-based multipath transmission scenario as claimed in claim 1, wherein: and under the preferential mode, selecting the most suitable transmission path as an effective transmission path according to the data certainty/time certainty evaluation and evaluation result of the transmission path.
6. The dynamic scheduling model in the DDS-based multiplexing scenario as claimed in claim 5, wherein: the preferred mode is one of the following modes, 1) one-way time delay is preferred; 2) one-way jitter is prior; 3) round-trip delay is prior; 4) round-trip jitter is prior; 5) the packet sending rate takes precedence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110262037.1A CN112929448B (en) | 2021-03-10 | 2021-03-10 | Dynamic scheduling method in DDS-based multipath transmission scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110262037.1A CN112929448B (en) | 2021-03-10 | 2021-03-10 | Dynamic scheduling method in DDS-based multipath transmission scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112929448A true CN112929448A (en) | 2021-06-08 |
| CN112929448B CN112929448B (en) | 2022-05-20 |
Family
ID=76172478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110262037.1A Active CN112929448B (en) | 2021-03-10 | 2021-03-10 | Dynamic scheduling method in DDS-based multipath transmission scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112929448B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101848236A (en) * | 2010-05-06 | 2010-09-29 | 北京邮电大学 | Real-time data distribution system with distributed network architecture and working method thereof |
| US20130132582A1 (en) * | 2011-11-18 | 2013-05-23 | Electronics And Telecommunications Research Institute | Apparatus and method for supporting qos in middleware for data distribution service |
| CN103166975A (en) * | 2013-04-03 | 2013-06-19 | 上海航天测控通信研究所 | Data distribution service (DDS) communication system |
| US20150373095A1 (en) * | 2014-06-24 | 2015-12-24 | Electronics And Telecommunications Research Institute | Method and apparatus for determining service quality profile on data distribution service |
| CN112468375A (en) * | 2021-01-26 | 2021-03-09 | 奥特酷智能科技(南京)有限公司 | Method for acquiring transmission performance evaluation data for data distribution service |
-
2021
- 2021-03-10 CN CN202110262037.1A patent/CN112929448B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101848236A (en) * | 2010-05-06 | 2010-09-29 | 北京邮电大学 | Real-time data distribution system with distributed network architecture and working method thereof |
| US20130132582A1 (en) * | 2011-11-18 | 2013-05-23 | Electronics And Telecommunications Research Institute | Apparatus and method for supporting qos in middleware for data distribution service |
| CN103166975A (en) * | 2013-04-03 | 2013-06-19 | 上海航天测控通信研究所 | Data distribution service (DDS) communication system |
| US20150373095A1 (en) * | 2014-06-24 | 2015-12-24 | Electronics And Telecommunications Research Institute | Method and apparatus for determining service quality profile on data distribution service |
| CN112468375A (en) * | 2021-01-26 | 2021-03-09 | 奥特酷智能科技(南京)有限公司 | Method for acquiring transmission performance evaluation data for data distribution service |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112929448B (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wei et al. | Shared bottleneck-based congestion control and packet scheduling for multipath TCP | |
| US8667165B2 (en) | Dynamic modification of application behavior in response to changing environmental conditions | |
| CN103476062B (en) | Data flow scheduling method, equipment and system | |
| CN111937364A (en) | Method and system for processing data path creation in wireless network system | |
| US20010056459A1 (en) | Service assignment apparatus | |
| Oh et al. | Constraint-based proactive scheduling for MPTCP in wireless networks | |
| US11259352B2 (en) | Systems, methods, and media for providing multi-homing | |
| KR20160062189A (en) | System and method for scheduling packet transmission on a client device | |
| WO2012145841A1 (en) | Hierarchical profiled scheduling and shaping | |
| Sun et al. | Enhancing the user experience in vehicular edge computing networks: An adaptive resource allocation approach | |
| EP3496432A1 (en) | Communication method and device | |
| EP2736196B1 (en) | Method and device for realizing multicast service | |
| Feldmann et al. | P4-enabled network-assisted congestion feedback: A case for nacks | |
| EP1589706B1 (en) | Control of multicast traffic | |
| CN102422604A (en) | Communication apparatus and communication control method | |
| CN112929448B (en) | Dynamic scheduling method in DDS-based multipath transmission scene | |
| CN103166872A (en) | Method for forwarding traffic in network and network equipment | |
| JP4681034B2 (en) | Bandwidth setting method and apparatus in class-based network | |
| JP2003110605A (en) | Policy control system, policy control method and program for allowing computer to execute the method | |
| US11627358B2 (en) | Communication entity and a method for transmitting a video data stream | |
| US20230291679A1 (en) | Dynamic use of a packet recovery mechanism to avoid congestion along a network path | |
| Heuschkel et al. | Beyond the core: Enabling software-defined control at the network edge | |
| CN101247325A (en) | Method and system for adding new service | |
| Paikan et al. | Communication channel prioritization in a publish-subscribe architecture | |
| KR101051712B1 (en) | Method for data transmission |
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 | ||
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 210012 room 401-404, building 5, chuqiaocheng, No. 57, Andemen street, Yuhuatai District, Nanjing, Jiangsu Province Patentee after: AUTOCORE INTELLIGENT TECHNOLOGY (NANJING) Co.,Ltd. Address before: 211800 building 12-289, 29 buyue Road, Qiaolin street, Pukou District, Nanjing City, Jiangsu Province Patentee before: AUTOCORE INTELLIGENT TECHNOLOGY (NANJING) Co.,Ltd. |