WO2024011162A1 - Mises à jour prédictives d'assignation d'un identifiant de trafic à une liaison dans des réseaux sans fil - Google Patents

Mises à jour prédictives d'assignation d'un identifiant de trafic à une liaison dans des réseaux sans fil Download PDF

Info

Publication number
WO2024011162A1
WO2024011162A1 PCT/US2023/069691 US2023069691W WO2024011162A1 WO 2024011162 A1 WO2024011162 A1 WO 2024011162A1 US 2023069691 W US2023069691 W US 2023069691W WO 2024011162 A1 WO2024011162 A1 WO 2024011162A1
Authority
WO
WIPO (PCT)
Prior art keywords
link
client sta
tid
client
communication link
Prior art date
Application number
PCT/US2023/069691
Other languages
English (en)
Inventor
Indermeet S. Gandhi
Robert E. Barton
Jerome Henry
Malcolm M. Smith
Original Assignee
Cisco Technology, Inc.
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from US18/345,650 external-priority patent/US20240015565A1/en
Application filed by Cisco Technology, Inc. filed Critical Cisco Technology, Inc.
Publication of WO2024011162A1 publication Critical patent/WO2024011162A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/06—Reselecting a communication resource in the serving access point
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/10—Small scale networks; Flat hierarchical networks
    • H04W84/12—WLAN [Wireless Local Area Networks]

Definitions

  • Embodiments presented in this disclosure generally relate to wireless communications. More specifically, embodiments disclosed herein related to systems and techniques for performing traffic management in a wireless network using predictive traffic identifier (TID)-to-link mapping.
  • TID predictive traffic identifier
  • Wireless communication standards such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 technical standard
  • IEEE 802.11 the Institute of Electrical and Electronics Engineers 802.11 technical standard
  • MLO multi-link operation
  • MLO enables devices, such as access points (APs) and client stations (STAs), to simultaneously send and receive data across different frequency bands and channels.
  • APs access points
  • STAs client stations
  • MLO multiple links can be established between the client STA and the same or different AP to increase throughput, reduce latency, and improve reliability.
  • MLO thus enables a multi-link AP logical entity and a multi-link non-AP logical entity to use multiple paths for user plane traffic.
  • Figure 1 illustrates an example system, according to one embodiment.
  • Figure 2 further illustrates certain components of the system depicted in Figure 1 , according to one embodiment.
  • Figure 3 illustrates an example graph of a performance metric of a client STA communicating over different communication links, according to one embodiment.
  • Figure 4 is a flowchart of a method for performing traffic management in a wireless network, according to one embodiment.
  • Figure 5 is a flowchart of another method for performing traffic management in a wireless network, according to one embodiment.
  • Figure 6 illustrates an example computing device, according to one embodiment.
  • the computer-implemented method includes obtaining one or more metrics associated with communication between a client station (STA) and an access point (AP) in a wireless network.
  • the communication between the client STA and the AP is based on a first traffic identifier (TID)-to-link map.
  • the computer-implemented method also includes determining a second TID-to-link map, different from the first TID-to-link map, based at least in part on evaluating the one or more metrics with a machine learning (ML) model.
  • the computer-implemented method further includes performing communications between the client STA and the AP, based on the second TID-to-link map.
  • the system includes a memory and a processor communicatively coupled to the memory.
  • the processor is configured to perform an operation.
  • the operation includes obtaining one or more metrics associated with communication between a client station (STA) and an access point (AP) in a wireless network.
  • the communication between the client STA and the AP is based on a first traffic identifier (TID)-to-link map.
  • TID traffic identifier
  • the operation also includes determining a second TID-to-link map, different from the first TID-to-link map, based at least in part on evaluating the one or more metrics with a machine learning (ML) model.
  • the operation further includes performing communications between the client STA and the AP, based on the second TID-to-link map.
  • the computer-readable storage medium includes computer executable code, which when executed by one or more processors, performs an operation.
  • the operation includes obtaining one or more metrics associated with communication between a client station (STA) and an access point (AP) in a wireless network.
  • the communication between the client STA and the AP is based on a first traffic identifier (TID)-to-link map.
  • TID traffic identifier
  • the operation also includes determining a second TID-to-link map, different from the first TID-to-link map, based at least in part on evaluating the one or more metrics with a machine learning (ML) model.
  • the operation further includes performing communications between the client STA and the AP, based on the second TID-to-link map.
  • Certain wireless systems may support traffic identifier (TID)-to-link mapping as a traffic management mechanism in wireless networks.
  • TID traffic identifier
  • MLO compliant devices may transmit, receive, or transit and receive with different quality-of-service (QoS) standards over multiple links. That is, different TIDs may be mapped to different links, in order to minimize, for example, access delays for time-sensitive traffic.
  • QoS quality-of-service
  • an AP may assign certain links (e.g., 5 gigahertz (GHz) link or 6 GHz link) to QoS-sensitive traffic (e.g., real-time collaborative applications, such as teleconferencing applications), and assign other links to other types of traffic, such as best effort traffic from a video streaming service.
  • links e.g., 5 gigahertz (GHz) link or 6 GHz link
  • QoS-sensitive traffic e.g., real-time collaborative applications, such as teleconferencing applications
  • TID-to-link mapping When a client STA is in close proximity to the AP, using TID-to-link mapping to allocate dedicated links for QoS-sensitive applications may be beneficial in terms of latency, throughput, and other application performance metrics.
  • the application performance may degrade and negatively impact the user experience.
  • One way to handle such client mobility situations may involve the AP waiting for the signal strength levels (e.g., received signal strength indication (RSSI) levels) on the link(s) allocated to QoS-sensitive traffic to fall below a certain threshold before moving the QoS-sensitive traffic to another link.
  • RSSI received signal strength indication
  • the application performance may have already degraded by the time the AP detects that signal strength levels have reached the particular threshold. Additionally, waiting for signal strength levels to reach a certain threshold can result in ping pong behavior between multiple links, which, in turn, can significantly impact the user experience (e.g., poor video quality, increased jitter, etc.) due in part to retries and potentially disconnection of the application.
  • embodiments described herein provide systems and techniques for performing traffic management in a wireless network using predictive TID-to-link mapping.
  • certain embodiments described herein provide techniques for using artificial intelligence (Al)/machine learning (ML) methods to accurately predict when application performance for a given link is going to degrade and to dynamically trigger switch of the application traffic to another link (e.g., before the application performance degrades).
  • switching application traffic to another link may be triggered by updating the TID-to- link map for the wireless network.
  • a node includes a wireless node.
  • Such wireless nodes may provide, for example, connectivity to or for a network (such as a wide area network (WAN) such as the Internet or a cellular network) via a wired or wireless communication link.
  • a wireless node may include an AP, a controller, or a client STA.
  • the terms “QoS-sensitive” application, “QoS- sensitive” application flow (or application traffic), and “QoS-sensitive” communication link (or link) may refer to an application, application flow, and communication link, respectively, that have a predefined QoS target or requirement.
  • the terms “non-QoS-sensitive” application, “non-QoS-sensitive” application flow (or application traffic), and “non-QoS-sensitive” communication link (or link) may refer to an application, application flow, and communication link, respectively, that do not have a predefined QoS target or requirement.
  • QoS-sensitive applications/application flows/communication links may not be able to tolerate the effects of packet loss, delay (also known as latency) (including delay variation or jitter), and fluctuations in network throughput without a degradation in application performance.
  • non-QoS-sensitive applications/application flows/communication links may be able to tolerate (a greater amount of) the effects of packet loss, delay (also known as latency) (including delay variation or jitter), and fluctuations in network throughput, compared to QoS-sensitive applications/application flows/communications, without a degradation in application performance.
  • a hyphenated form of a reference numeral refers to a specific instance of an element and the un-hyphenated form of the reference numeral refers to the collective element.
  • device “12-1” refers to an instance of a device class, which may be referred to collectively as devices “12” and any one of which may be referred to generically as a device “12”.
  • FIG. 1 illustrates an example system 100 in which one or more techniques described herein can be implemented, according to one embodiment.
  • the system 100 includes one or more APs (e.g., AP 102-1 , AP 102-2, and AP 102-3), one or more client STAs (e.g., client STA 104-1 , client STA 104-2, client STA 104-3, and client STA 104-4), a controller 130, and one or more databases 140.
  • An AP is generally a fixed station that communicates with client STA(s) and may be referred to as a base station, wireless device, or some other terminology.
  • a client STA may be fixed or mobile and also may be referred to as a mobile STA, a client, a STA, a wireless device, or some other terminology. Note that while a certain number of APs and client STAs are depicted, the system 100 may include any number of APs and client STAs.
  • the downlink (e.g., forward link) is the communication link from the AP 102 to the client STA(s) 104
  • the uplink (e.g., reverse link) is the communication link from the client STA(s) 104 to the AP 102.
  • a client STA may also communicate peer-to-peer with another client STA.
  • each client STA 104 includes one or more radios 108.
  • the client STA 104 can use one or more of the radios 108 to form links 150 with an AP 102.
  • each AP 102 includes one or more radios 112 that the AP 102 can use to form links 150 with one or more client STAs 104.
  • the AP(s) 102 and the client STA(s) 104 may form any suitable number of links 150 for communication using any suitable frequencies or bands.
  • a client STA 104 may form multiple links 150 with a single AP 102.
  • a client STA 104-1 can use a first radio 108-1 operating on a first band (e.g., 5 GHz band) to establish a first link 150-1 with AP 102-1 , a second radio 108-2 operating on a second band (e.g., 6 GHz band) to establish a second link 150-2 with the AP 102-1 , a third radio 108-3 operating on a third band (e.g., 2.4 GHz band) to establish a third link 150-3 with the AP 102-1 , and so on.
  • a first band e.g., 5 GHz band
  • a second radio 108-2 operating on a second band (e.g., 6 GHz band) to establish a second link 150-2 with the AP 102-1
  • a third radio 108-3 operating on a third band (e.g., 2.4 GHz band) to establish a third link 150-3 with the AP 102-1
  • the controller 130 couples to and provides coordination and control for the APs 102 1-3.
  • the controller 130 may handle adjustments to RF power, channels, authentication, and security for the APs.
  • the controller 130 may also assign and coordinate the links 150 formed by the client STA(s) 104 with the APs 102.
  • the controller 130 can perform or handle traffic management for the APs 102 1-3.
  • the controller 130 can generate and transmit (updated) TID-to-link maps to the APs 102 1-3.
  • the TID-to- link map(s) may indicate which application traffic is allocated to a given communication link between the APs 102 1-3 and their respective client STAs.
  • the controller 130 may be communicatively coupled to (or integrated with) one or more databases 140.
  • the database(s) 140 are representative of storage systems that may include information on one or more communication links in the system 100.
  • the database(s) 140 may include different types of metrics, including application performance metrics (e.g., frame retransmission counters, jitter, latency, delay, etc.), communication link metrics (e.g., RSSI, modulation and coding scheme (MCS), etc.), sensing metrics (e.g., channel state information (CSI) data, sensing reports, etc.), list of applications, or a combination thereof.
  • application performance metrics e.g., frame retransmission counters, jitter, latency, delay, etc.
  • communication link metrics e.g., RSSI, modulation and coding scheme (MCS), etc.
  • sensing metrics e.g., channel state information (CSI) data, sensing reports, etc.
  • CSI channel state information
  • the database(s) 140 may also include logic (e.g., AI/ML models) for (i) predicting when application performance on a communication link will degrade, (ii) generating (updated) TID-to-link maps to switch application traffic to another link, or (iii) a combination thereof.
  • logic e.g., AI/ML models
  • the controller 130 is included within or integrated with an AP 102 and coordinates the links 150 formed by that AP 102 (or otherwise provides control for that AP).
  • each AP 102 may include a controller that provides control for that AP.
  • the controller 130 is separate from the APs 102 and provides control for those APs.
  • the controller 130 may communicate with the APs 102 1-3 via a (wired or wireless) backhaul.
  • the APs 102 1-3 may also communicate with one another, e.g., directly or indirectly via a wireless or wireline backhaul.
  • Example hardware that may be included in a controller 130 is discussed in greater detail with regard to Figure 6.
  • the system 100 supports MLO operation in which multiple links 150 can be established between the client STA and the same or different AP to allow for concurrent data transmission and reception.
  • one or more of the client STAs 104 may be referred to as STA multi-link devices (MLDs) (e.g., a STA or client device acting as a MLD) and/or one or more of the APs 102 may be referred to as AP MLDs (e.g., an AP that acts as a MLD).
  • MLDs multi-link devices
  • AP MLDs e.g., an AP that acts as a MLD
  • the STA MLD and AP MLD are generally representative of any device capable of performing multi-link operations.
  • a MLD may generally be classified based on whether it is a single radio MLD or multiradio MLD.
  • Single radio MLDs generally use a single radio to switch between one or more links.
  • One category of single radio MLDs is Enhanced Multi-Link Single Radio (eMLSR).
  • eMLSR devices generally operate one main wireless radio that can transmit and/or receive data frames on a given link, but can detect some data (e.g., short initial frames) on a set of other links when the device is not actively transmitting or receiving.
  • Multi-radio MLDs may generally be classified into the following two types: (i) simultaneous transmission and reception (STR) MLD and (ii) non-STR MLD.
  • STR MLDs simultaneous transmission and reception
  • a transmission on one link may not affect the operations of frame reception and clear channel assessment (CCA) on other links.
  • CCA clear channel assessment
  • individual links can operate independently of each other.
  • the system can use AI/ML techniques to accurately predict when the application performance will start to degrade and to dynamically trigger a switch of the application to another communication link (e.g., via an updated TID-to-link map), before the application performance degrades.
  • the system 100 includes a prediction component 230, which is configured to perform one or more techniques described herein.
  • the prediction component 230 may include hardware, software, or combinations thereof.
  • the prediction component 230 is integral with the controller 130.
  • the prediction component 230 is external to and communicatively coupled to the controller 130 and/or the database 140.
  • the prediction component 230 may be included in a cloud computing environment.
  • the application metrics collected by the AP 102-1 may include application type, frame (re)-transmission counters, jitter, latency, frame delay, and mean opinion score (MOS), as illustrative, nonlimiting examples.
  • the AP 102-1 may transmit a message 220 with an indication of the collected application metrics to the prediction component 230.
  • a remote server (not shown) can report the application metrics to the prediction component 230.
  • the remote server may be integral to or otherwise communicatively coupled to the controller 130.
  • the AP may also collect communication link metrics associated with one or more communication links established between the AP 102 and client STA(s) 104.
  • the AP 102-1 may initially assign a 6 GHz low power indoor (LPI) link or a 5 GHz link to QoS- sensitive applications (e.g., video teleconferencing, ARA/R applications, cloud gaming, etc.).
  • the AP 102-1 may assign lower performance or coverage links (e.g., 6 GHz standard power (SP) link or 2.4 GHz link) to non-QoS-sensitive applications (e.g., streaming application).
  • SP standard power
  • the AP 102-1 may communicate this default policy to the client STA 104-4 using a (initial) TID-to-link-map.
  • the AP 102-1 may continually collect communication link metrics, such as signal strength (e.g., RSSI), MCS, and number of retransmissions, as illustrative, non-limiting examples, on each of the wireless communication links 150 established with the client STA 104-1. Additionally, in certain embodiments, the AP 102-1 can obtain one or more sensing metrics (e.g., CSI data, sensing reports, etc.) associated with mobility of the client STA 104-1. In one example, the AP 102-1 can measure the CSI for the client STA 104-1 in order to determine the client STA’s movement.
  • the AP 102-1 can determine whether the client STA is moving towards the AP, such as from location B to location A, or whether the client STA is moving away from the AP, such as from location A to location B.
  • the AP 102-1 can perform periodic sensing feedback (e.g., in accordance with IEEE 802.11 bf sensing request/feedback protocol) with the client STA 104-1 to determine the client STA’s movement.
  • the AP 102-1 may perform periodic sensing on the QoS-sensitive link and with client STAs 104 that have QoS-sensitive applications running. This correlation of movement sensing to the QoS-sensitive links may form the basis of a classification system to predict the optimal link according to one or more metrics for each application.
  • the AP 102-1 may transmit, to the prediction component 230, a message 240 with an indication of the communication link metrics, sensing metrics, or a combination thereof.
  • the prediction component 230 may use the collected metrics (e.g., application metrics, communication link metrics, sensing metrics, or a combination thereof) to train an AI/ML model(s) to (i) predict when application performance will start to degrade, (ii) predict which communication link will meet an optimal application-level performance (according to one or more metrics), or (iii) a combination thereof.
  • the prediction component 230 may use a variety of AI/ML techniques to train an AI/ML model including, for example, neural networks, logistic regression, and gradient boosting algorithms, as illustrative, nonlimiting examples.
  • the prediction component 230 uses the collected metrics to train an AI/ML model that results in a classification of which communication link to use for application traffic that will meet an optimal level of performance for the application.
  • this classification is in the form of an updated TID-to-link map.
  • the prediction component 230 may transmit a message 210 with an indication of the updated TID-to-link map to the AP 102-1.
  • the AP 102-1 may then use the updated TID-to-link map to switch the application traffic from the client STA 104-2 to another link.
  • the application traffic may be switched from communication link 150-1 to one of communication links 150 2-K, based on the updated TID-to-link map.
  • the communication link 150-1 may be associated with a different radio of the AP 102-1 than each of the communication links 150 2-K.
  • the prediction component 230 can collect the various metrics in a data set that is used to train an AI/ML model.
  • the ML model may be an edge application or a central model for the entire cell 110.
  • the prediction component 230 can deploy the AI/ML model at the AP 102-1.
  • the AP 102- 1 may use the AI/ML model to analyze current metrics, including CSI, RSSI, etc., and to output a TID-to-link map that indicates which communication link 150 to move an application flow to.
  • the trained AI/ML model can be deployed at the client STA 104-1.
  • the client STA 104-1 can use the trained AI/ML model to analyze current metrics and to output a TID-to-link map that indicates which communication link 150 to move an application flow to.
  • FIG. 3 illustrates an example graph 300 of a performance metric (e.g., RSSI) of a client STA 104 communicating over different communication links, according to one embodiment.
  • a performance metric e.g., RSSI
  • FIG. 3 illustrates an example graph 300 of a performance metric (e.g., RSSI) of a client STA 104 communicating over different communication links, according to one embodiment.
  • graph 300 uses RSSI as an example of a performance metric
  • CSI performance metrics
  • the client STA 104 is associated with communication link 150-1 (e.g., 6 GHz LPI communication link) and communication link 150-2 (e.g., 6 GHz SP communication link).
  • the client STA 104 may use communication link 150-1 to run QoS- sensitive application(s).
  • the trained AI/ML model may predict what the RSSI levels (as well as other metrics) of the client STA 104 will be at subsequent second time instance (t2) and subsequent third time instance (ts), for each of the communication links 150 1-2.
  • the trained AI/ML model may determine that, at the third time instance (ts), (i) the communication link 150-1 will be unsuitable for the QoS-sensitive application and (ii) the communication link 150-2 will be suitable for the QoS- sensitive application.
  • the trained AI/ML model may output a predictive command to the AP 102 to adjust the TID-to-link map for the client STA 104 (e.g., prior to time instance ts), as the existing communication link 150-1 may not be suitable for QoS-sensitive communication and the application performance may begin to degrade by time instance ts.
  • the TID-to- link map may be updated so that the QoS-sensitive application is moved from the communication link 150-1 (e.g., 6 GHz LPI communication link) to the communication link 150-2 (e.g., 6 GHz SP communication link or 2.4 GHz communication link) at time instance ts.
  • the trained AI/ML model may output a predictive command to the AP 102 to adjust the TID-to-link map for other client STAs using non-QoS-sensitive links, so that the non-QoS-sensitive links can be made available for QoS-sensitive traffic.
  • the trained AI/ML model can update the TID-to-link maps of other client STAs 104 that are closer to the AP to move some of their non-QoS-sensitive applications to a QoS-sensitive link (if available).
  • the TID-to-link maps of other client STAs 104 using non-QoS-sensitive links are updated at time instance ts, so that the non-QoS- sensitive links can be made available for QoS-sensitive traffic.
  • the trained AI/ML model can recommend to push certain applications to a communication link on another radio (e.g., 5 GHz communication link).
  • Figure 4 is a flowchart of an example method 400 for performing traffic management in a wireless network using predictive TID-to-link mapping, according to one embodiment.
  • Method 400 may be performed by a prediction component (e.g., prediction component 230).
  • Method 400 enters at block 402, where the prediction component obtains one or more metrics associated with communication of a client STA (e.g., client STA 104) with an AP (e.g., AP 102).
  • the metrics may include application metrics, communication link metrics, sensing metrics, list of applications running on the client STA, or a combination thereof.
  • the prediction component trains an AI/ML model, based on the one or more metrics, to predict performance changes and TID-to-link mapping.
  • the trained AI/ML model may be an initial AI/ML model that is trained based on the one or more metrics.
  • the trained AI/ML model may be an updated AI/ML model that is trained based on the one or more metrics.
  • the prediction component provides the trained AI/ML model to at least one of the client STA or the AP.
  • the trained AI/ML model may be deployed at the AP.
  • the trained AI/ML model may be deployed at the client STA.
  • the prediction component determines whether one or more additional metrics have been obtained. For example, as noted, the prediction component may continually obtain RF data (e.g., CSI, RSSI, SNR, etc.) and application metrics (e.g., application type, jitter, latency, etc.) as the client STA moves (e.g., within cell 110). In one embodiment, the prediction component may check for additional metrics based on a time interval, event, or some other criteria. If additional metrics have been obtained, the prediction component may train an updated AI/ML model at block 404. On the other hand, if additional metrics have not been obtained, the method 400 may exit.
  • RF data e.g., CSI, RSSI, SNR, etc.
  • application metrics e.g., application type, jitter, latency, etc.
  • Figure 5 is a flowchart of an example method 500 for performing traffic management in a wireless network using predictive TID-to-link mapping, according to one embodiment.
  • Method 500 may be performed by a computing device (e.g., prediction component 230, client STA 104, AP 102).
  • a computing device e.g., prediction component 230, client STA 104, AP 1012.
  • Method 500 enters at block 502, where the computing device assigns application traffic from a client STA to a first communication link, based on a first TID-to-link map.
  • the application traffic may be QoS-sensitive application traffic from an application running on the client STA and may have a predefined (or target) performance criteria (e.g., QoS target).
  • the first communication link may be associated with a first radio of the AP that is configured to at least one of (i) operate on a first band (e.g., 6 GHz) or (ii) operate using a first transmission power scheme (e.g., LPI operation).
  • the computing device obtains one or more metrics associated with the client STA.
  • the one or more metrics may include at least one of (i) one or more metrics associated with one or more applications running on the client STA, (ii) one or more metrics associated with one or more communication links established between the client STA and the AP, or (iii) one or more metrics associated with wireless sensing feedback from the client STA.
  • the computing device determines a second TID-to-link map, based on evaluating the one or more metrics with a trained AI/ML model.
  • the AI/ML model may be trained using a dataset that includes at least one of (i) a set of application metrics, (ii) a set of communication link metrics, or (iii) a set of wireless sensing feedback.
  • the trained AI/ML model may output at least one of (i) an indication of a time instance when the first communication link will not satisfy the predefined performance criteria associated with the application traffic from the client STA or (ii) an indication of a second communication link established between the client STA and the AP that satisfies the predefined performance criteria associated with the application traffic from the client STA.
  • the computing device assigns the application traffic from the client STA to a second communication link, based on the second TID-to-link map.
  • assign the application traffic to the second communication link may include moving the application traffic from the first communication link to the second communication link prior to the time instance in which the application performance is predicted to degrade.
  • the second TID-to-link map may be associated with a second radio of the AP that is configured to operate on a second band (e.g., 5 GHz or 2.4 GHz).
  • the second communication link may be associated with the second radio of the AP that is configured to operate on the second band.
  • the second TID-to-link map may be associated with a second radio of the AP that is configured to operate on the first band (e.g., 6 GHz) using a second transmission power scheme (e.g., SP operation).
  • the second communication link may be associated with the second radio of the AP that is configured to operate on the first band using the second transmission power scheme.
  • FIG. 6 illustrates an example computing device 600, according to one embodiment.
  • the computing device 600 can be configured to perform one or more techniques described herein for performing traffic management using predictive TID- to-link mapping.
  • the computing device 600 can perform method 400, method 500, and any other techniques (or combination of techniques) described herein.
  • the computing device 600 can be an AP (e.g., AP 102), a client STA (e.g., client STA 104), or a controller (e.g., controller 130).
  • the computing device 600 includes a processor 610, a memory 620, and one or more radios 630a-n (generally, radio 630).
  • the processor 610 may be any processing element capable of performing the functions described herein.
  • the processor 610 represents a single processor, multiple processors, a processor with multiple cores, and combinations thereof.
  • the radios 630 facilitate communications between the computing device 600 and other devices.
  • the radios 630 are representative of communication interferences, such as wireless communications antennas and various wired communication ports.
  • the memory 620 may be either volatile or non-volatile memory and may include RAM, flash, cache, disk drives, and other computer readable memory storage devices. Although shown as a single entity, the memory 620 may be divided into different memory storage elements such as RAM and one or more hard disk drives.
  • the memory 620 includes various instructions that are executable by the processor 610 to provide an operating system 622 to manage various functions of the computing device 600.
  • the memory 620 also includes a prediction component 230, one or more application(s) 626, one or more TID-to-link maps 640, one or more metrics 650 (e.g., application metrics, communication link metrics, wireless sensing feedback, or a combination thereof), and a trained AI/ML model(s) 660.
  • embodiments described herein provide techniques and systems for predictive TID-to-link mapping.
  • an AI/ML model based on observed RF metrics as well as available data corresponding to various applications, to predict performance changes and perform TID-to-link mapping
  • embodiments can significantly improve the performance of communications in wireless networks.
  • the trained AI/ML model can be pushed to AP(s) and/or STA(s), which can use the trained AI/ML model to proactively select an updated TID-to-link map before application performance degrades.
  • the trained AI/ML model can be continually consulted to find the optimal TID-to-link map for the client STA.
  • a computer-implemented method comprising: obtaining one or more metrics associated with communication between a client station (STA) and an access point (AP) in a wireless network, wherein the communication between the client STA and the AP is based on a first traffic identifier (TID)-to-link map; determining a second TID-to-link map, different from the first TID-to-link map, based at least in part on evaluating the one or more metrics with a machine learning (ML) model; and performing communications between the client STA and the AP, based on the second TID-to-link map.
  • TID traffic identifier
  • ML machine learning
  • Clause 2 The computer-implemented method of Clause 1 , wherein: the first TID-to-link map allocates traffic from a first application running on the client STA to a first communication link established between the client STA and the AP; and the second TID-to-link map allocates the traffic from the first application running on the client STA to a second communication link established between the client STA and the AP.
  • Clause 3 The computer-implemented method of Clause 2, wherein performing communications between the client STA and the AP comprises moving the traffic from the first communication link to the second communication link.
  • Clause 4 The computer-implemented method of any of Clauses 2 to 3, wherein: the first communication link is associated with a first radio of the AP that is configured to operate on a first band; and the second communication link is associated with a second radio of the AP that is configured to operate on a second band.
  • Clause 5 The computer-implemented method of any of Clauses 2 to 4, wherein: the first communication link is associated with a first radio of the AP that is configured to operate on a first band using a first transmission power scheme; and the second communication link is associated with a second radio of the AP that is configured to operate on the first band using a second transmission power scheme.
  • Clause 6 The computer-implemented method of any of Clauses 1 to 5, wherein the ML model is configured to output at least one of (i) an indication of a time instance when a first communication link established the client STA and the AP will not satisfy a target performance criteria for an application running on the client STA or (ii) an indication of a second communication link established between the client STA and the AP that satisfies a target performance criteria for an application running on the client STA.
  • Clause 9 The computer-implemented method of any of Clauses 1 to 8, wherein the one or more metrics comprise at least one of (i) one or more first metrics associated with one or more applications running on the client STA, (ii) one or more second metrics associated with one or more communication links established between the client STA and the AP, or (iii) one or more third metrics associated with wireless sensing feedback from the client STA.
  • Clause 10 A system comprising a processor configured to perform the computer-implemented method of any of Clauses 1 to 9.
  • Clause 11 A computer-readable medium comprising computer executable code, which when executed by one or more processors, causes performance of the computer-implemented method of any of Clauses 1 to 9.
  • embodiments disclosed herein may be embodied as a system, method or computer program product. Accordingly, embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, embodiments may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.
  • Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).
  • LAN local area network
  • WAN wide area network
  • Internet Service Provider for example, AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other device to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function/act specified in the block(s) of the flowchart illustrations and/or block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

L'invention concerne des systèmes et des techniques de gestion de trafic dans un réseau sans fil à l'aide d'un mappage prédictif d'assignation d'un identifiant de trafic (TID) à une liaison. Une technique donnée à titre d'exemple consiste à obtenir un ou plusieurs indicateurs associés à une communication entre une station (STA) client et un point d'accès (AR) dans un réseau sans fil. La communication entre la STA client et l'AR est basée sur une première carte d'assignation de TID à une liaison. Une seconde carte d'assignation de TID à une liaison est déterminée, sur la base, au moins en partie, de l'évaluation du ou des indicateurs à l'aide d'un modèle d'apprentissage automatique. Des communications entre la STA client et l'AR sont effectuées, sur la base de la seconde carte d'assignation de TID à une liaison.
PCT/US2023/069691 2022-07-08 2023-07-06 Mises à jour prédictives d'assignation d'un identifiant de trafic à une liaison dans des réseaux sans fil WO2024011162A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US202263367996P 2022-07-08 2022-07-08
US63/367,996 2022-07-08
US18/345,650 US20240015565A1 (en) 2022-07-08 2023-06-30 Predictive traffic identifier-to-link updates in wireless networks
US18/345,650 2023-06-30

Publications (1)

Publication Number Publication Date
WO2024011162A1 true WO2024011162A1 (fr) 2024-01-11

Family

ID=87557857

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2023/069691 WO2024011162A1 (fr) 2022-07-08 2023-07-06 Mises à jour prédictives d'assignation d'un identifiant de trafic à une liaison dans des réseaux sans fil

Country Status (1)

Country Link
WO (1) WO2024011162A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210014911A1 (en) * 2019-07-12 2021-01-14 Qualcomm Incorporated Multi-link communication
WO2021182892A1 (fr) * 2020-03-11 2021-09-16 엘지전자 주식회사 Techniques pour réaliser une communication à liaisons multiples dans un système de communication sans fil
WO2021185211A1 (fr) * 2020-03-16 2021-09-23 华为技术有限公司 Procédé et dispositif de transmission de données
US20220124855A1 (en) * 2020-10-15 2022-04-21 Facebook Technologies, Llc Methods and systems for multi-link operations

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210014911A1 (en) * 2019-07-12 2021-01-14 Qualcomm Incorporated Multi-link communication
WO2021182892A1 (fr) * 2020-03-11 2021-09-16 엘지전자 주식회사 Techniques pour réaliser une communication à liaisons multiples dans un système de communication sans fil
US20230115361A1 (en) * 2020-03-11 2023-04-13 Lg Electronics Inc. Technique for performing multi-link communication in wireless communication system
WO2021185211A1 (fr) * 2020-03-16 2021-09-23 华为技术有限公司 Procédé et dispositif de transmission de données
US20220124855A1 (en) * 2020-10-15 2022-04-21 Facebook Technologies, Llc Methods and systems for multi-link operations

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LOPEZ-RAVENTOS ALVARO ET AL: "Multi-Link Operation in IEEE 802.11be WLANs", IEEE WIRELESS COMMUNICATIONS, COORDINATED SCIENCE LABORATORY; DEPT. ELECTRICAL AND COMPUTER ENGINEERING; UNIVERSITY OF ILLINOIS AT URBANA-CHAMPAIGN, US, vol. 29, no. 4, 6 May 2022 (2022-05-06), pages 94 - 100, XP011924090, ISSN: 1536-1284, [retrieved on 20220506], DOI: 10.1109/MWC.006.2100404 *

Similar Documents

Publication Publication Date Title
US10979124B2 (en) Forward error correction code selection in wireless systems
EP3310009B1 (fr) Cadre de travail d'ingénierie de la circulation dans un réseau défini par logiciel
US10362588B2 (en) Determining a threshold value for determining whether to steer a particular node from associating with one node to another node in a wireless environment
US9155019B2 (en) Combining bandwidth aware routing with channel selection and switching in a multi-hop wireless home network
KR20200018220A (ko) 무선 통신 시스템에서 네트워크 트래픽 관리 방법 및 장치
US11290915B2 (en) Systems and methods for granular beamforming across multiple portions of a radio access network based on user equipment information
US9338769B1 (en) Method of scheduling communication in a wireless communication network
JP2014216709A (ja) 通信装置、マルチホップ無線通信ネットワークシステム及び通信方法
US10548028B2 (en) Establishing backhaul connection to mesh points and mesh portals on different wireless communication channels
US9264960B1 (en) Systems and methods for determinng access node candidates for handover of wireless devices
Bukhari et al. QoS based approach for LTE-WiFi handover
US11576055B2 (en) Method, apparatus and computer readable media for network optimization
US20240015565A1 (en) Predictive traffic identifier-to-link updates in wireless networks
US9973971B2 (en) Methods, nodes and system for enabling redistribution of cell load
WO2024011162A1 (fr) Mises à jour prédictives d'assignation d'un identifiant de trafic à une liaison dans des réseaux sans fil
US11743786B1 (en) Dynamic handover parameter adjustment based on amount of packet drops at dual-connectivity access node pair
Khasawneh et al. Predictive congestion avoidance in wireless mesh network
Passos et al. Robust Advanced Metering Infrastructures and Networks for Smart Grid
Venugopalan et al. Interference mitigation with spectrum sharing and aggregation for SDN based cognitive networks
US11405087B1 (en) Systems and methods for dynamically adjusting reporting periodicity
US20230370317A1 (en) Automated management of uplink technologies for optimal experience
US10966138B2 (en) Data communication and resource management in hybrid infrastructure and neighbor awareness networking networks
US20240172016A1 (en) Prediction of cell traffic in a network
US9820201B1 (en) Systems and methods for performing a handover based on target configuration
Ren et al. QoS-guaranteed Clustering and Routing Protocol for Extended Sensor Sharing in Vehicular Networks

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23751473

Country of ref document: EP

Kind code of ref document: A1