Unified Channel Score

Abstract

Embodiments of this disclosure relate to unified channel scoring. Techniques for a network management system (NMS) are disclosed, in which the NMS calculates a channel score based on a normalized metric for the channel and assigns the channel to an access point (AP) based on the channel score. In one example, the NMS obtains data associated with at least one of a plurality of channels in a frequency band at a site, wherein the data includes a set of metrics. The NMS calculates a normalized metric for each metric in the metric set relative to a threshold representing a performance degradation of at least one channel. The NMS calculates a channel score based on the product of the normalized metrics. The NMS assigns the channel to at least one AP based on the channel score.

Description

Cross-references to related applications

[0001] This application claims the benefit of U.S. Patent Application No. 19 / 402199, filed November 26, 2025, and U.S. Provisional Patent Application No. 63 / 752398, filed January 31, 2025, the entire contents of each of which are incorporated herein by reference. Technical Field

[0002] This disclosure generally relates to computer networks, and more specifically, to radio resource management in wireless networks. Background Technology

[0003] Commercial locations or sites (such as offices, hospitals, airports, stadiums, or retail stores) often install complex wireless network systems (including networks of wireless access points (APs)) throughout the premises to provide wireless network services to one or more wireless client devices (or simply "clients"). An AP is a physical electronic device that enables other devices to wirelessly connect to a wired network using various wireless networking protocols and technologies, such as Wi-Fi (compliant with IEEE 802.11), Bluetooth / Bluetooth Low Energy (BLE), mesh networking protocols (such as ZigBee), or other wireless networking technologies.

[0004] To provide a wireless network, an access point (AP) is configured to conduct wireless communication in one or more wireless frequency bands (e.g., the 2.4 GHz band, the 5 GHz band, and / or the 6 GHz band). Each frequency band consists of multiple channels. At any given time, an AP can be assigned to operate on a specific channel (e.g., transmit and receive wireless signals) among the multiple channels within each of the one or more wireless frequency bands. Summary of the Invention

[0005] Generally, this disclosure describes a technique for a network management system (NMS) for wireless networks to allocate (multiple) wireless channels to an access point (AP) based on a channel score indicating the quality of each channel within a frequency band. Conventional channel allocation systems may only consider a limited number of types of interference, such as non-WIFI (e.g., radar) interference detected on the operational channel of the AP's data radio and / or interference from neighboring APs. Using limited data from limited sources may result in the allocation of operational channels to APs where the allocated channels may be protected from a limited number of types of interference, but may still suffer from low-quality performance.

[0006] The disclosed technology enables NMS to allocate channels based on a view of the radio frequency (RF) environment, rather than simply based on interference detected on the AP's operating channels. This RF environment includes Wi-Fi and non-Wi-Fi interference, noise, and other performance metrics observed by at least one continuously scanning radio on all channels within the radio band. The network management system obtains metrics regarding the quality of the channels within the radio band and calculates normalized metrics. NMS uses these normalized metrics to calculate channel scores for the channels within the radio band and allocates channels to the AP's data radios based on these channel scores.

[0007] The technology disclosed herein can provide one or more technical advantages for implementing at least one practical application. For example, the technology enables an NMS to optimize channel allocation to an AP based on assessments of multiple sources of performance degradation. Compared to using only data radio readouts, the NMS can use data based on scanned radio readouts, data based on data radio readouts, and / or data from third parties to gain relatively greater visibility into the RF environment. The NMS can use this data to improve the performance of the wireless network (e.g., the performance of wireless connectivity to client devices provided by the AP) by allocating channels relatively unaffected by various types of interference. In another example, the technology enables the NMS to avoid selecting channels that suffer from a specific type of performance degradation but are not affected by other types of performance degradation. In yet another example, the technology enables the NMS to perform root cause analysis to determine the cause of performance degradation detected in one or more channels and generate notifications and / or recommendations to address the performance degradation.

[0008] Details of one or more examples of the technology disclosed herein are illustrated in the accompanying drawings and the following description. Other features, objects, and advantages of the technology will be apparent from the specification, drawings, and claims. Attached Figure Description

[0009] Figure 1A This is a diagram of an example network system according to one or more techniques of this disclosure, wherein channels are assigned to access points based on channel scores.

[0010] Figure 1B It is shown Figure 1A A block diagram providing further examples and details of the network system.

[0011] Figure 2 This is a block diagram of an example access point based on one or more technologies according to this disclosure.

[0012] Figure 3 This is a block diagram of an example network management system based on one or more technologies disclosed herein.

[0013] Figure 4 This is a block diagram of an example user equipment device according to one or more technologies of this disclosure.

[0014] Figure 5 This is a block diagram of an example network node, such as a router or switch, based on one or more technologies according to this disclosure.

[0015] Figures 6A to 6B It is a graph of example indicators of wireless channels according to one or more technologies of this disclosure.

[0016] Figure 7 It is a collection of graphs of example indicators of wireless channels within a wireless frequency band according to one or more techniques of this disclosure.

[0017] Figure 8 It is a collection of graphs of example indicators, including prediction indicators of wireless channels within a wireless band, based on one or more techniques of this disclosure.

[0018] Figure 9 This is a flowchart illustrating an example operation for determining channel allocation based on one or more techniques disclosed herein. Detailed Implementation

[0019] Figure 1A This is a diagram of an example network system 100 according to one or more techniques of this disclosure, wherein channels are assigned to access points (APs) based on channel scores. The example network system 100 includes multiple network sites 102A-102N (alternatively referred to as "sites 102A-102N"), at which a network service provider manages one or more wireless networks 106A-106N respectively. Although in Figure 1A In this disclosure, each site 102A-102N is shown as including a single corresponding wireless network 106A-106N, but in some examples, each site 102A-102N may also include multiple wireless networks, and this disclosure is not limited in this respect.

[0020] Each site 102A-102N includes multiple network access server (NAS) devices 108A-108N, such as access points (APs) 142, switches 146, or routers 147. NAS devices 108 may include any network infrastructure device capable of authenticating and authorizing client devices to access the corporate network. For example, site 102A includes multiple APs 142A-1 to 142A-M. Similarly, site 102N includes multiple APs 142N-1 to 142N-M. Each AP 142 can be any type of wireless access point, including but not limited to commercial or enterprise APs, routers, or any other device connected to a wired network and capable of providing wireless network access to client devices within the site.

[0021] To provide wireless network 106, AP 142 is configured to conduct wireless communication in one or more wireless frequency bands. For example, the wireless frequency bands may include, but are not limited to, the 2.4 GHz band, the 5 GHz band, the 6 GHz band, and / or any other lower or higher frequency bands. Each frequency band consists of multiple channels. At any given time, each AP 142 is assigned to operate on a specific channel among the multiple channels (e.g., transmitting and receiving wireless signals). Channel allocation may be implemented by, for example, a radio resource manager (RRM) 134 of NMS 130, or another RRM, or a similar module of one or more NAS devices 108, or another computing device configured to manage radio resources in the wireless network.

[0022] Each site 102A-102N also includes multiple client devices (also known as user equipment devices (UEs), generally referred to as client device 148 or UE 148, representing various wireless-enabled devices within each site). For example, multiple UEs 148A-1 to 148A-N are currently located at site 102A. Similarly, multiple UEs 148N-1 to 148N-N are currently located at site 102N. Each UE 148 can be any type of wireless client device, including but not limited to mobile devices such as smartphones, tablets or laptops, personal digital assistants (PDAs), wireless terminals, smartwatches, smart rings, or other wearable devices. UE 148 may also include IoT client devices such as printers, security devices, environmental sensors, appliances, or any other device configured to communicate on one or more wireless networks 106.

[0023] To provide wireless network services to UE 148 and / or communicate on wireless network 106, AP 142 and other wired client-side devices at site 102 are directly or indirectly connected to one or more network devices (e.g., switches, routers, gateways, etc.) via physical cables (e.g., Ethernet cables). Figure 1A In the example, site 102A includes switch 146A, one or more of APs 142A-1 to 142A-M at site 102A can be connected to switch 146A, and switch 146A can then be connected to router 147A. Similarly, site 102N includes switch 146N, one or more of APs 142N-1 to 142N-M at site 102N can be connected to switch 146N, and switch 146N can then be connected to router 147N. Although in Figure 1A The illustration appears to show each site 102 including a single switch 146 and a single router 147; however, in other examples, each site 102 may also include more or fewer switches and / or routers. Furthermore, access points (APs) and other wired client-side devices at a given site may connect to two or more switches and / or routers. In some examples, interconnected switches and routers comprise a wired local area network (LAN) at site 102 hosting the wireless network 106. Additionally, two or more switches at a site may interconnect and / or connect to two or more routers, and two or more routers may interconnect and / or (e.g., via a mesh or partial mesh topology in a hub-and-spoke architecture) connect to other routers at other sites, thereby forming at least a portion of a wide area network (WAN).

[0024] Example network system 100 also includes various networking components for providing networking services within a wired network, including, for example, an Authentication, Authorization and Accounting (AAA) server 110 for authenticating users and / or UE 148, a Dynamic Host Configuration Protocol (DHCP) server 116 for dynamically assigning network addresses (e.g., IP addresses) to UE 148 after authentication, a Domain Name System (DNS) server 122 for resolving domain names to network addresses, multiple servers 128A-128X (collectively referred to as "Server 128") (e.g., web server, database server, file server, etc.), and an NMS 130. Figure 1AAs shown, various devices and systems of network system 100 are coupled together via one or more networks 104 (e.g., the Internet and / or corporate intranets).

[0025] exist Figure 1A In the example, NMS 130 is a cloud-based computing platform for managing wireless networks 106A-106N at one or more of sites 102A-102N. As further described herein, NMS 130 provides an integrated suite of management tools and implements various technologies disclosed herein. Generally, NMS 130 can provide a cloud-based platform for wireless network data acquisition, monitoring, activity logging, reporting, predictive analytics, network anomaly identification, and alarm generation. In some examples, NMS 130 outputs notifications (such as alerts, alarms, graphical indicators on dashboards, log messages, text / SMS messages, email messages, etc.) and / or suggestions regarding wireless network issues to site or network administrators (“management”) who interact with and / or operate management device 111. Additionally, in some examples, NMS 130 operates in response to configuration input received from administrators who interact with and / or operate management device 111.

[0026] The NMS 130 monitors network data associated with the wireless networks 106A-106N at each site 102A-102N to provide a high-quality wireless network experience to end users, IoT devices, and clients at the sites. Network data can include multiple states or parameters indicative of one or more aspects of wireless network performance. Data can be acquired, collected, and / or received from numerous sources, including client devices, access points (APs), switches, routers, gateways, firewalls, etc. Network data can be stored in a database such as the network data storage 136 within the NMS 130, or alternatively, in an external database. Generally, the NMS 130 can provide a cloud-based platform for network data acquisition, monitoring, activity logging, reporting, predictive analytics, network anomaly identification, and alert generation. In some examples, the NMS 130 uses a combination of artificial intelligence, machine learning, and data science techniques to optimize user experience and streamline operations across any one or more of the wireless access domain, wired access domain, and software-defined wide area network (SD-WAN) domain.

[0027] The administrator and management device 111 may include IT personnel and administrator computing devices associated with one or more sites 102. The management device 111 may be implemented as any suitable device for presenting output and / or accepting user input. For example, the management device 111 may include a display. The management device 111 may be a computing system, such as a mobile or non-mobile computing device operated by a user and / or administrator. According to one or more aspects of this disclosure, the management device 111 may, for example, represent a workstation, laptop or notebook computer, desktop computer, tablet computer, or any other computing device that can be operated by a user and / or present a user interface. The management device 111 may be physically separate from the NMS 130 and / or located in a different location from the NMS 130, such that the management device 111 can communicate with the NMS 130 via network 104 or other communication means.

[0028] In some examples, one or more NAS devices 108 (e.g., AP 142, switch 146, and router 147) may be connected to edge devices 150A-150N via physical cables (e.g., Ethernet cables). Edge devices 150 include cloud-managed wireless local area network (LAN) controllers. Each edge device 150 may include a provisioned device at site 102 that communicates with NMS 130 to extend certain microservices from NMS 130 to the provisioned NAS devices 108, while using NMS 130 and its distributed software architecture for scalable and resilient operation, management, troubleshooting, and analysis.

[0029] Each network device in network system 100 (e.g., AP 142, switch 146, router 147, UE 148, edge device 150, and any other server or device attached to or forming part of network system 100) may include a system log or error log module, wherein each of these network devices records the status of the network device, including normal operating status and error conditions. In this disclosure, one or more network devices of network system 100 (e.g., AP 142, switch 146, router 147, and UE 148) may be considered "third-party" network devices when owned and / or associated with an entity different from NMS 130, such that NMS 130 does not directly receive, collect, or otherwise access the recorded status and other data of the third-party network devices. In some examples, edge device 150 may provide a proxy through which the recorded status and other data of the third-party network devices can be reported to NMS 130.

[0030] Although the technology of this disclosure is described in this example as being performed by NMS 130, the technology described herein can also be performed by any other computing device(s), system, and / or server(s), and this disclosure is not limited thereto. For example, one or more computing devices configured to perform the technology of this disclosure may reside in a dedicated server, or may be included in any other server besides or different from NMS 130, or may be distributed throughout the network system 100 and may or may not be part of NMS 130.

[0031] NMS 130 may include a virtual network assistant (VNA) 132, which analyzes network data received from one or more NAS devices 108 (in some cases, UE 148) in the wireless network to provide real-time insights and simplified troubleshooting for IT operations, and automatically takes remedial action or provides recommendations to proactively resolve wireless network problems. VNA 132 may, for example, include a network data processing platform configured to process hundreds or thousands of concurrent network data streams from UE 148, sensors and / or agents associated with AP 142, and / or nodes within network 104. Example SLE metrics may include connection time, throughput, successful connections, capacity, AP health, and / or any other metrics that may indicate one or more aspects of wireless network performance. Network service providers may further implement systems that automatically identify the root causes(s) of any SLE metric(s) that do not meet thresholds, and / or automatically implement one or more remedial actions to address the root causes, thereby automatically improving wireless network performance. In some examples, VNA 132 may obtain SLE data from one or more client devices 148.

[0032] AP 142, managed by NMS 130, may experience interference on one or more radio channels used by AP 142. AP 142 may experience one or more types of interference, such as interference caused by neighboring APs using AP 142's data radio for transmission. For example, AP 142A-1 may experience interference on the radio channel assigned to AP 142A-1. As a result of AP 142A-M using the same channel as AP 142A-1 to transmit to a client device (e.g., UE 148), AP 142A-1 may experience interference. AP 142 may include information about the experienced interference in the network data provided to NMS 130.

[0033] As part of managing the wireless channel allocation for AP 142, NMS 130 can reallocate wireless channels for AP 142. NMS 130 can determine the wireless channel based in part on information about channel interference received from AP 142. In one example, AP 142A-1 experiences interference on its assigned operational channel within the 5 GHz band. NMS 130 receives network information from AP 142A-1 indicating that the AP is experiencing interference on its assigned channel. NMS 130 determines that the interference experienced by AP 142A-1 is consistent with radar interference and blacklists the operational channel to prevent its use at the site. NMS 130 then determines a different channel allocation for AP 142A-1 to avoid the blacklisted channel and instructs AP 142A-1 to switch to the updated channel allocation.

[0034] In some examples, NMS 130 can determine channel allocation for AP 142 on a periodic basis. NMS 130 can determine channel allocation for some or all of AP 142 based on one or more factors, such as interference associated with the channel, whether the channel is blacklisted, and / or other factors. For example, NMS 130 can determine channel allocation for AP 142 on a daily basis based on analysis performed by modules of NMS 130, such as Radio Resource Manager 134.

[0035] The Radio Resource Manager (RRM) 134 of the NMS 130 can monitor one or more metrics at each site 102A-102N to learn and optimize the RF environment at each site. For example, RRM 134 can monitor coverage and capacity SLE metrics for wireless network 106 at site 102 based on interference observed by the data radio of AP 142 to identify potential problems with SLE coverage and / or capacity in wireless network 106. RRM 134 can use interference observed by the scanning radio of AP 142 to adjust the radio settings of the access points at each site to address the identified problems. For example, RRM 134 can determine the channel and transmit power distribution of all APs 142 across each wireless network 106A-106N. RRM 134 can monitor events, power, channels, bandwidth, and the number of clients connected to each AP. RRM 134 can further automatically change or update the configuration of one or more APs 142 at site 102 for the purpose of improving coverage and capacity SLE metrics, thereby providing users with an improved wireless experience.

[0036] Conventional techniques for channel allocation may lack visibility into the full picture of the RF environment, including noise, interference, and performance issues across all channels within the radio band. Such techniques may only use interference data from the operational channels of the AP's data radio. Conventional techniques may allocate channels to the AP without considering other types of interference and / or performance issues across all channels in the radio band. Furthermore, channels allocated using conventional techniques may perform well relative to a specific type of interference but may still suffer from other types of interference or performance issues that degrade channel quality.

[0037] According to the techniques described in this disclosure, NMS 130 obtains data including a set of metrics associated with at least one channel in the frequency band. RRM 134 calculates a channel score based on a normalized metric representing channel quality and assigns the channel to AP 142 based on the channel score. RRM 134 can calculate a normalized metric based on the obtained metrics for use in calculating the channel score.

[0038] NMS 130 can obtain data associated with channels in a frequency band from various sources within network system 100. NMS 130 can obtain data from sources including the scanning radio of AP 142, the data radio of AP 142, sensors, non-WIFI systems, third-party application servers, and / or other sources. For example, NMS 130 can obtain continuous scanning radio readings from the scanning radio of AP 142, rather than just data radio readings from the data radio of AP 142. NMS 130 can obtain data associated with multiple channels within one or more WIFI frequency bands. In one example, AP 142A-1 uses scanning radio and data radio to generate data on the performance of multiple channels within each frequency band, where the data includes metrics about channel performance. NMS 130 obtains the data generated by AP 142A-1 and stores it in network data storage 136.

[0039] The NMS 130 can acquire data including a set of metrics associated with wireless channels in a frequency band at a site, wherein the set of metrics is related to various performance indicators of the channels. The NMS 130 can acquire a set of metrics including non-Wi-Fi metrics, noise floor metrics, undecodeable Wi-Fi metrics, unknown Wi-Fi metrics, and / or other types of metrics. The NMS 130 can acquire data including a set of metrics for multiple channels within each of multiple frequency bands (e.g., acquiring a set of metrics for one or more channels in the 2.4 GHz band, a set of metrics for one or more channels in the 5 GHz band, a set of metrics for one or more channels in the 6 GHz band, etc.).

[0040] In some examples, the NMS 130 obtains data from sources different from the scanning radio and data radio of the AP 142. The NMS 130 can obtain data from a variety of sources, including access points or network access devices not managed by the NMS 130, radar systems, application servers, Automated Frequency Coordination (AFC) systems, electronic shelf label (ESL) systems, Fast Fourier Transform (FFT) dynamic scanning, or radio frequency (RF) spectrum capture, and / or other sources. The NMS 130 can obtain data including RF spectrum data, third-party data from the application server, and / or client connectivity data derived from SLE metrics. For example, the NMS 130 can obtain data from two or more of the aforementioned sources for use in determining channel allocation.

[0041] The NMS 130 can use the RRM 134 to calculate normalized indices for one or more indices in a set of indices. For example, the RRM 134 can calculate normalized indices for indices associated with interference observed by the scanning radio of the AP 142. The RRM 134 can calculate a normalized indice for each indice, where the normalized indice represents the channel quality relative to the corresponding indice. The RRM 134 can use one or more equations to calculate the normalized indices, such as Equation 1 below:

[0042] in x These are the raw values ​​of the indicator. k "Threshold" is a predetermined steepness scalar, and "threshold" is a value corresponding to a relevant threshold for degradation performance (e.g., a threshold determined by RRM 134, the administrator, and / or other entities). RRM 134 may determine the threshold in one or more ways, such as by using historical data to determine the percentile of the metric. In some examples, RRM 134 may filter the percentile of the data to include only data from sites with the minimum number of APs (e.g., to ignore smaller sites or test sites).

[0043] In some examples, RRM 134 can verify whether normalized values ​​reflect the distribution. RRM 134 can group by scan channel and average the scores of each normalized metric to see the resulting channel score for each metric. RRM 134 can compare the channel scores of a metric to the distribution of the metric's original values ​​to verify that the scores effectively represent the site's behavior. In one example, RRM 134 determines the scan noise floor score of a site where channels 40-120 have a better distribution, with most scan noise floor values ​​between -100 and -90; channels 130-140 have a slightly worse distribution, with most scan noise floor values ​​between -90 and -80; and channels 140-160 have an anomalous distribution, with most scan noise floor values ​​between -80 and -60 (e.g., relatively high channel scores).

[0044] RRM 134 can use one or more equations to compute a normalized metric that is normalized to values ​​between 0 and 1, where values ​​close to 0 represent optimal and / or “normal” values ​​for performance, and values ​​close to 1 represent non-optimal or “outlier” values ​​for performance. For example, RRM 134 can compute a normalized metric relative to a threshold representing the degraded performance of a channel, where the normalized metric represents the channel quality relative to the corresponding channel. RRM 134 can use a sigmoid function to demonstrate that the score increases sharply as the original value approaches the threshold, while still maintaining a low score within the normal range. For example, RRM 134 can compute a normalized value close to 1 for the noise floor of a wireless channel, representing a relatively high noise floor that is not optimal for wireless transmission.

[0045] RRM 134 calculates channel scores based on normalized metrics. RRM 134 can analyze data regarding interference and / or application performance and use this data to calculate a score for each channel (e.g., 0 = the channel is ideal for an access point to transmit on it, 1 = the channel is poor for an access point to transmit on it). RRM 134 can calculate the channel score for each channel based on the normalized metrics associated with the channel and using a product formula. RRM 134 can use one or more types of equations to calculate the product formula, such as Equation 2 below: The “score” here refers to the channel score. RRM 134 can use one or more equations to calculate the “metric score,” such as Equation 3 below: (Equation 3) Each score aggregated into an "Indicator Score" is a normalized metric based on an indicator obtained from network data storage 136. For example, RRM 134 can use a "Non-WIFI Score" as a normalized value for interference from sources different from the WIFI transmitter (e.g., weather radar), a "Noise Basis Score" as a normalized value in dBm of the noise basis of the channel interference, and a "Non-Decoding WIFI Score" as a normalized value indicating WIFI interference from a hidden WIFI network to calculate the "Indicator Score" for the channel. In some examples, RRM 134 can calculate additional or alternative normalized metrics (such as client application performance metrics) to be included when calculating the "Indicator Score". RRM 134 can use the above equations to calculate normalized metrics representing the quality of the channel based on scan radio readings and / or data radio readings from AP 142.

[0046] RRM 134 can use a product formula instead of the standard linear weighting formula, so that if any score is poor (e.g., close to 1), it is appropriately represented in the total channel score. For example, RRM 134 can use a product formula to identify from the data how poor one metric is that the channel is unusable, but how normal other metrics are. Furthermore, RRM 134 can use a product formula to allow additional metrics to be included in the channel score, where the linear scoring formula becomes increasingly impractical as the uniformly distributed weights of each metric continue to decrease.

[0047] RRM 134 can periodically generate updated channel scores. RRM 134 can update channel scores on a periodic basis (e.g., hourly, daily, etc.), with the score from the most recent hour used for any local / instantaneous updates in channelization. For example, RRM 134 can use scores from the most recent 24 hours to facilitate global optimization.

[0048] In some examples, RRM 134 can generate forecast channel scores that indicate predicted channel performance at one or more future time points. RRM 134 can use one or more ML models to process historical data for one or more metrics to determine one or more forecast channel scores. In one example, RRM 134 obtains historical data including metrics associated with the performance of the wireless channel over a predetermined time period. RRM 134 applies an ML model to the historical data to determine forecast channel scores that indicate predicted channel scores at future time points. RRM 134 can use the forecast channel scores to determine channel allocations at times different from peak demand (e.g., client wireless connectivity demand). As part of a channel reallocation process performed during off-peak demand periods, RRM 134 can determine forecast channel scores for use in proactively determining channel allocations for peak demand periods. In one example, NMS 130 determines channel allocations for the following day during a nighttime period when wireless connectivity demand is low. RRM 134 generates forecast channel scores to provide a reference for proactively determining channel allocations for upcoming peak wireless connectivity demand periods during the following day.

[0049] RRM 134 can allocate channels to AP 142 based on channel scores. RRM 134 can determine channel allocation based on one or more factors, such as whether the channel score exceeds a predetermined threshold, whether the channel score has increased compared to a previously calculated channel score, the detection of events associated with the channel, and / or other factors. For example, RRM 134 can allocate or reallocate channels based on SLE data calculated by NMS 130 and based on network data from AP 142. RRM 134 can reallocate channels and / or perform initial channel allocation based on channel scores. For example, if the channel score associated with a given channel exceeds a predetermined threshold, RRM 134 can suppress the allocation of a given channel to one of APs in AP 142.

[0050] In some examples, RRM 134 assigns channels to AP 142 based on time windows. RRM 134 can determine the channel score for a channel within a time window and assign channels for second and subsequent time windows based on the channel score of previous time windows. In one example, RRM 134 determines the channel score for a previous time window (e.g., a time window prior to the current time window). RRM 134 assigns channels to APs based on the channel score for the previous time window.

[0051] The techniques disclosed herein can provide one or more technical advantages for achieving at least one practical application. For example, using data associated with interference experienced by the scanning radio of AP 142 can provide relatively greater visibility into the RF environment of the site compared to using only data radio, where the scanning radio scans and collects data for each channel within the frequency band, while the data radio only scans and collects data for the currently operating channel of the radio. Furthermore, greater visibility into the RF environment allows NMS 130 to avoid allocating wireless channels with relatively poor quality (e.g., relatively high levels of interference). NMS can use this data to improve the performance of the wireless network (e.g., the performance of wireless connectivity to client devices provided by the AP) by allocating channels relatively unaffected by multiple types of interference. In another example, calculating channel scores based on normalized metrics allows NMS 130 to avoid allocating channels with specific types of degraded performance to AP 142 (e.g., allocating channels affected by one type of performance degradation but unaffected in other respects). Further, normalization of metrics allows NMS 130 to consider metrics with different units and scales (e.g., scales for “acceptable” levels of interference or performance degradation). In yet another example, using forecast channel scores enables the NMS 130 to determine channel allocations during off-peak demand periods, thereby proactively reallocating channels before peak wireless connectivity demand and / or utilization periods to maximize wireless network performance.

[0052] Figure 1B It is shown Figure 1A A block diagram illustrating further details of the network system. See above for reference. Figure 1A As described, according to one or more techniques disclosed herein, the NMS 130 of the radio resource management module 134 optimizes one or more operating parameters of the AP 142 in the wireless network 106 on a per-channel basis.

[0053] In this example, Figure 1B An NMS 130 configured to operate based on an AI / machine learning-based computing platform is shown, which provides wireless network 106 and wired LAN 175 networks from the network edge. Figure 1B (The far left) crosses over to cloud-based application services 181 hosted by computing resources within data center 179. Figure 1BThe rightmost section provides comprehensive automation, insights, and assurance (Wi-Fi assurance, wired assurance, and WAN assurance). NMS 130 includes a Virtual Network Assistant 132, a Radio Resource Management Module 134, Network Data 136, and Channel-Specific Operating Parameters 138. Channel-Specific Operating Parameters 138 include one or more optimized operating parameters determined and / or applied according to one or more techniques of this disclosure, specific to each channel within a given frequency band.

[0054] As described herein, NMS 130 provides an integrated set of management tools and implements various technologies disclosed herein. Generally, NMS 130 can provide a cloud-based platform for wireless network data acquisition, monitoring, activity logging, reporting, predictive analytics, network anomaly identification, and alarm generation. For example, the network management system 130 can be configured to proactively monitor and adaptively configure network system 100 to provide self-driving capabilities. Furthermore, VNA 133 includes a natural language processing engine to provide AI-driven support and troubleshooting, anomaly detection, AI-driven location services, and AI-driven RF optimization utilizing reinforcement learning.

[0055] In some examples, NMS 130 may obtain data from a third-party source for use in determining channel allocation. NMS 130 may obtain data, including application performance data (e.g., data about the performance of the video conferencing application), from a third-party source such as a video conferencing application provider. In one example, NMS 130 generates a request for information and provides it to a server associated with the third party. The third party generates data including metrics about the performance of the client application and provides this data to NMS 130 for consumption. RRM 134 obtains the data and uses the included metrics when determining the channel allocation for the AP.

[0056] Figure 2 This is a block diagram of an example access point (AP) 200 configured according to one or more technologies disclosed herein. Figure 2 The example access point 200 shown can be used to implement as described in this document. Figure 1A Any of the AP 142 shown and described. Access point 200 may include, for example, a Wi-Fi, Bluetooth and / or Bluetooth Low Energy (BLE) base station, or any other type of wireless access point.

[0057] exist Figure 2In the example, access point 200 includes a wired interface 230, wireless interfaces 220A-220B (alternately referred to as "data radio"), a scanning radio 290 (alternately referred to as "continuous scanning radio"), one or more processors 206, memory 212, and a user interface 210 coupled together via bus 214. These components can exchange data and information on bus 214. Wired interface 230 represents a physical network interface and includes a receiver 232 and a transmitter 234 for sending and receiving network communications (e.g., packets). Wired interface 230 directly or indirectly couples access point 200 to... Figure 1A The network 104 (multiple networks). Wireless interfaces 220A-220N represent wireless network interfaces and each includes receivers 222A-222N, each including a receiving antenna. Access point 200 can receive signals from wireless communication devices (such as...) via the receiving antennas. Figure 1A The access point 200 can receive wireless signals from UE 148, other instances of AP device 200, and / or any other wireless device. Wireless interfaces 220A-220N also include transmitters 224A-224N, each including a transmitting antenna. The access point 200 can transmit signals to wireless communication devices (such as UE 148, other instances of AP device 200, and / or any other wireless device) via the transmitting antenna. Figure 1A (UE 148, other instances of AP 200, and / or any other wireless device) transmit wireless signals. In some examples, wireless interfaces 220A-220N may include one or more Wi-Fi 802.11 interfaces (e.g., 2.4 GHz and / or 5 GHz), one or more Bluetooth interfaces, and / or Bluetooth Low Energy (BLE) interfaces. One or more of interfaces 220A-220N can be used to perform RTT measurements. However, these are given for illustrative purposes only, and this disclosure is not limited in this respect.

[0058] AP 200 can use the data radio of wireless interface 220 to observe the channel used by wireless interface 220 for data transmission. AP 200 can use the data radio of wireless interface 220 to observe one or more types of interference in AP 200's wireless environment, such as non-WIFI interference, undecodeable WIFI interference, unknown WIFI interference, noise floor of the wireless environment, and / or other types of interference, and generate data based on the recorded interference. For example, AP 200 can use the data radio of wireless interface 220A to observe the wireless channel assigned to AP 200 and generate data about the channel's performance. AP 200 can use the data radio of wireless interface 220 to generate relatively more detailed data compared to AP 200's scanning radio (e.g., because AP 200's data radio can be tuned to a specific channel with a longer frequency than AP 200's scanning radio).

[0059] The scanning radio 290 can be a component of the AP 200, which listens to or scans the AP 200's wireless environment. The AP 200 can use the scanning radio 290 to observe multiple channels in its wireless environment for use in generating data that includes metrics about the AP 200's wireless environment. The AP 200 can generate data based on the quality or performance of channels scanned by the scanning radio 290, in addition to those assigned to the wireless interface. For example, the AP 200 can use the scanning radio to record interference observed on each channel in its wireless environment. The AP 200 can use the data radio of the wireless interface 220 to generate relatively more detailed data about the assigned or current channels, and use the scanning radio 290 to generate relatively less detailed data about multiple channels in a frequency band (e.g., the scanning radio 290 may observe many channels during the same time period in which the data radio obtains data about a more limited number of channels). For example, the AP 200 can use the data radio to record interference observed on operational channels. Although shown as a separate component, in some examples, the AP 200 may also use one or more wireless interfaces 220 as scanning radios 290.

[0060] The processors 206 are processors based on programmable hardware configured to execute software instructions (such as software instructions for defining software or computer programs) stored in a computer-readable storage medium (such as memory 212), such as non-transitory computer-readable media including storage devices (e.g., disk drives or optical disk drives) or memories (such as flash memory or RAM), or storing instructions to cause one or more processors 206 to perform one or more of the techniques described herein, in any other type of volatile or non-volatile memory.

[0061] Memory 212 includes one or more devices configured to store programming modules and / or data associated with the operation of access point 200. For example, memory 212 may include computer-readable storage media, such as non-transitory computer-readable media, including storage devices (e.g., disk drives or optical disk drives) or memories (such as flash memory or RAM), or any other type of volatile or non-volatile memory that stores instructions to cause one or more processors 206 to perform one or more of the techniques described herein.

[0062] In this example, memory 212 stores executable software and / or data, including an application programming interface (API) 240, a communication manager 242, configuration / radio settings 250, channel operation parameters 252, network data 254, and data storage 256. In some examples, network data 254 includes any type of data measured or collected by AP 200, including, for example, received signal strength indicator (RSSI) of wireless signals received from one or more other APs in the wireless network, and RSSI of wireless signals received from one or more wireless clients (UEs). For example, AP 200 may store data including metrics about the quality (e.g., performance) of one or more channels in network data 254. Data 256 may further store any data used and / or generated by access point 200, including data collected from UE 148 and / or one or more other APs 200.

[0063] AP 200 can send signals to NMS (such as...) Figures 1A to 1B The NMS 130 shown provides data about the channel quality. In one example, the AP 200 uses data radio and scanning radio to record information about interference in the channel within a frequency band. The AP 200 generates data including metrics about the channel quality and provides this data to the NMS 130.

[0064] The communication manager 242 includes program code that, when executed by the processor(s) 206, allows the access point 200 to communicate with the UE 148, other APs 142, and / or the network(s) 104 via any of the interfaces(s) 230 and / or 220A-220B. Configuration settings 250 include any device settings for the access point 200, such as the default or adjusted radio settings for each of the radio interfaces(s) 220A-220B. According to one or more techniques of this disclosure, channel-specific operating parameters 252 include one or more optimized operating parameters (e.g., transmit power optimization) determined for each specific channel in a given frequency band according to one or more techniques of this disclosure. In events where the AP 200 is configured to communicate on multiple frequency bands (such as the 2.4 GHz band, the 5 GHz band, and / or the 6 GHz band), the channel-specific operating parameters 252 may include channel-specific operating parameters for each frequency band on which the AP 200 is configured to communicate.

[0065] These channel-specific optimized operating parameters can be obtained, for example, from an execution reference. Figure 1A and Figure 1B The NMS 130 of the described radio resource management module 134 is determined. In some examples, the optimized operating parameters stored in the channel operating parameters are updated on a continuous, periodic, or scheduled basis.

[0066] AP 200 can receive channel assignments from NMS 130. NMS 130 can determine one or more channel assignments for AP 200 based on data and / or other information received from AP 200 and provide AP 200 with instructions on the channel assignments. AP 200 can reconfigure one or more components (e.g., wireless interface 220) to operate according to the channel assignments.

[0067] Input / output (I / O) 210 represents the physical hardware components that enable interaction with the user, such as buttons, touchscreens, displays, etc. Although not shown, memory 212 typically stores executable software used to control the user interface with respect to inputs received via I / O 210.

[0068] Figure 3 This is a block diagram of an example network management system (NMS) 300 according to one or more technologies disclosed herein. The NMS 300 is configured to optimize one or more operating parameters of multiple access points (APs) in a wireless network on a per-channel basis. For example, the NMS 300 is configured to optimize one or more operating parameters of multiple APs based on a specific channel allocation for each AP. The NMS 300 can be used to implement, for example... Figures 1A to 1B The NMS 130 is mentioned. In this example, the NMS 300 is responsible for monitoring and managing one or more wireless networks 106A-106N at sites 102A-102N. In some examples, the NMS 300 receives network data 315 collected by AP142 / 200 and analyzes this data for cloud-based management of wireless networks 106A-106N. In some examples, the NMS 300 may be... Figure 1A , Figure 1B It is part of another server shown, or part of any other server.

[0069] The NMS 300 includes a communication interface 330, one or more processors 306, a user interface 310, a memory 320, and a database 318. The various components are coupled together via a bus 314, on which they can exchange data and information.

[0070] Database 318 includes storage for data related to the monitoring and management of wireless network 106. Network data 315 includes any type of data measured or collected by AP 142 / 200, including, for example, Received Signal Strength Indication (RSSI) of wireless signals transmitted between AP 142, RSSI of wireless signals transmitted between AP 142 and UE 148, etc. Data 256 may further store any data used and / or generated by access point 200, including data collected from UE 148 and / or one or more other AP 200. According to one or more techniques of this disclosure, channel-specific operating parameters 317 include one or more optimized operating parameters (e.g., transmit power optimization) determined for each specific channel of a given frequency band. In some examples, channel-specific operating parameters 317 include channel-specific operating parameters for each of one or more frequency bands (such as the 2.4 GHz band, 5 GHz band, or 6 GHz band and / or any other wireless band).

[0071] Multiple processors 306 execute software instructions (such as software instructions for defining software or computer programs) stored in a computer-readable storage medium (such as memory 320), such as a non-transitory computer-readable medium including storage devices (e.g., disk drives or optical disk drives) or memory (such as flash memory or RAM), or store instructions to cause one or more processors 306 to perform the techniques described herein, in any other type of volatile or non-volatile memory.

[0072] The communication interface 330 may include, for example, an Ethernet interface. The communication interface 330 couples the NMS 300 to a network and / or the Internet, such as... Figure 1A Any (or multiple) networks 104 shown, and / or any local area network. Communication interface 330 includes receiver 332 and transmitter 335. NMS 300 communicates with / from AP 142, servers 110, 116, 122, 128, and / or forms a network system 100 (such as...) via receiver 332 and transmitter 335. Figures 1A to 1B The NMS 300 may send / receive data and information to any other device or system within the network sites 102A-102N (as shown). The data and information received by the NMS 300 may include, for example, network data and / or event log data received from AP 142 used by the NMS 300 to remotely monitor and / or control the performance of the wireless networks 106A-106N and determine the location of AP 142. The NMS may further send data via communication interface 330 to any network device (such as AP 142) at any of the network sites 102A-102N to remotely manage the wireless networks 106A-106N.

[0073] Memory 320 includes one or more devices configured to store programming modules and / or data associated with the operation of NMS 300. For example, memory 320 may include computer-readable storage media, such as non-transitory computer-readable media, including storage devices (e.g., disk drives or optical disk drives) or memories (such as flash memory or RAM), or any other type of volatile or non-volatile memory that stores instructions to cause one or more processors 306 to perform the techniques described herein.

[0074] In this example, memory 312 includes API 320, SLE module 322, Radio Resource Management module (RRM) 334, Virtual Network Assistant (VNA) / AI engine 350, location engine 370, and one or more machine learning models 380. NMS 300 may also include any other programming modules, software engines, and / or interfaces configured to remotely monitor and manage wireless networks 106A-106N (including remote monitoring and management of any AP142).

[0075] RRM 334 monitors one or more metrics at each site 102A-102N to learn and optimize the power and / or radio frequency (RF) environment at each site. For example, RRM 334 can monitor coverage and capacity SLE metrics (e.g., managed by SLE module 322) of wireless network 106 at site 102 to identify potential problems with coverage and / or capacity in wireless network 106 and adjust the radio settings of AP 142 at each site to address the identified problems. RRM 334 can determine the channel and transmit power distribution of all AP 142 across each network 106A-106N. RRM 334 can monitor events, power, channels, bandwidth, and the number of clients connected to each AP device. RRM 334 can measure the strength of radio signals from client devices, such as RSSI values. RRM 334 can further automatically change or update the configuration of one or more AP 142 at site 102 for the purpose of improving coverage and / or capacity SLE metrics, thereby providing users with an improved wireless experience.

[0076] In some examples, RRM 334 can provide metrics such as those included in Table I below: Table I RRM 334 can organize metrics based on the time when the metric was observed by the relevant AP (e.g., the "timestamp" in Table I), the AP's identifier (e.g., "003F160A14" in Table I), and the scanning channel associated with the metric when applicable (e.g., when the metric was observed by the AP's scanning radio). In the example in Table I, RRM 334 organizes AP 003F160A14's non-WIFI metrics, noise-based metrics, undecodeable WIFI metrics, and unknown WIFI metrics according to the scanning channel and the time the metric was observed.

[0077] According to one or more techniques disclosed herein, RRM 334 also includes program instructions that, when executed by one or more processors of NMS300 and / or any other computing device, determine channel allocation for the AP based on a channel score. For example, RRM 334 may calculate a normalized metric based on an obtained set of observed metrics for the channel, and calculate a channel score representing the quality of the channel based on the normalized metric. RRM 334 then allocates the channel to the AP based on the channel score. In some examples, RRM 334 may further generate a notification indicative of the channel allocation for display on a user computing device associated with, for example, an IT technician.

[0078] The VNA / AI engine 350 analyzes network data received from AP 142 and its own data to monitor the performance of wireless networks 106A-106N. For example, the VNA engine 350 can identify when an abnormal or anomalous state is encountered in one of the wireless networks 106A-106N. The VNA / AI engine 350 can use a root cause analysis module (not shown) to identify the root cause of any abnormal or anomalous state. In some examples, the root cause analysis module utilizes artificial intelligence-based techniques to help identify the root cause of any(s) poor SLE metrics at one or more locations in wireless networks 106A-106N. Furthermore, the VNA / AI engine 350 can automatically invoke one or more remedial actions designed to resolve the root cause of the identified one or more poor SLE metrics. Examples of remedial actions that can be automatically invoked by the VNA / AI engine 350 may include, but are not limited to, invoking RRM 334 to restart one or more AP devices and / or adjust / modify the transmit power of a specific radio in a specific AP device, adding a service set identifier (SSID) configuration to a specific AP device, changing the channel on an AP device or a set of AP devices, etc. Remedial measures may also include restarting the switch and / or router, invoking new software downloads to the AP device, switch, or router, etc. These remedies are given for illustrative purposes only, and this disclosure is not limited in this respect. If automated remedies are unavailable or insufficient to address the root cause, the VNA / AI Engine 350 can proactively and automatically provide notifications including suggested remedial actions to be taken by IT personnel to address the abnormal or anomalous wireless network operation.

[0079] SLE (Service Level Experience) module 322 establishes and tracks thresholds for one or more SLE (e.g., performance) metrics for each of the wireless networks 106A-106N. SLE module 322 further analyzes network data collected (e.g., stored as network data 315) by AP devices and / or UEs associated with the wireless networks 106A-106N (such as any AP142 from UE 148 in each wireless network 106A-106N). For example, APs 142A-1 to 142A-N collect network data (e.g., named assets, connected / unconnected Wi-Fi clients) from UEs 148A-1 to 148A-N currently associated with the wireless network 106A. This data, except for any network data collected by one or more APs 142A-1 to 142A-N in the wireless network 106A, is sent to NMS 300 and stored as, for example, network data 315.

[0080] The NMS 300 executes the SLE module 322 to determine one or more SLE metrics for each UE 148 associated with the wireless network 106. These SLE metrics can be further aggregated to each AP device at the site to gain insight into the contribution of each AP device to the wireless network performance at the site. The SLE metrics track whether the service level of each specific SLE metric meets one or more configured thresholds. In some examples, each SLE metric may also include one or more classifiers. If a metric fails to meet the SLE thresholds configured for the site, the failure can be attributed to one of the classifiers to further understand how and / or why the failure occurred.

[0081] In some examples, RRM 334 uses the SLE metric when determining channel allocation. RRM 334 can obtain the SLE metric from SLE module 322 and include the SLE metric when calculating the channel score. For example, RRM 334 can calculate a normalized metric of the SLE metric and generate the channel score based on the product of the normalized SLE metric and other normalized metrics (e.g., undecodeable Wi-Fi).

[0082] In some examples, the RRM 334 uses additional metrics when calculating the channel score. The RRM 334 may use metrics including, but are not limited to, continuous scan radio readings (e.g., from...). Figure 2 The scan radio readings shown are from 290 scanning radio, and the data radio readings (e.g., from...) Figure 2 The data from AP 200 includes radio readings, external Basic Service Set Identifiers (BSSIDs) (e.g., access points or network devices not managed by NMS 300), radar systems, third-party application data (e.g., from application servers), Automatic Frequency Coordination (AFC) for 6 GHz WIFI systems, and data from ESL systems within the site (e.g., WIFI data from shelf labels or other components of ESL systems, Bluetooth Low Energy data, etc.), and / or dynamic scanning or RF spectrum capture performed by one or more components (which may or may not be included in AP 142) using Fast Fourier Transform (FFT) or other methods.

[0083] In one example, RRM 334 normalizes an indicator included in data from two or more sources and uses that indicator to calculate the channel score as described above. In another example, RRM 334 calculates a first channel score based on interference data obtained from a continuous scan radio (as described above) and an indicator based on a second channel score included in data obtained from a second source. In this example, RRM 334 may correlate or combine the first and second channel scores to provide a final channel score based on both the first and second sources. In some scenarios, the second source may be a data radio reading of interference data observed against the operational channel of an AP. Operational channel interference data may be more accurate than interference data observed by a continuous scan radio on the same AP against the same channel. RRM 334 may combine interference data from data radio and continuous scan radios from the same channel to obtain empirical and / or refined interference data for the channel.

[0084] In some examples, the NMS 300 can acquire historical data for the RRM 334 to generate forecast channel scores and store the historical data. The NMS 300 can acquire historical data including one or more types of metrics relating channel performance to a time period (e.g., minutes, hours, days, etc.) and store the historical data in database 318 for use in generating forecast channel scores. In one example, the NMS 300 acquires historical data including metrics about unknown Wi-Fi interference and non-Wi-Fi interference experienced on a specific channel over a predetermined time period, as well as other metrics. The NMS 300 provides the historical data to the RRM 334 for processing to determine a forecast channel score for a specific channel based on the metrics included in the historical data.

[0085] The VNA / AI engine 350 can perform root cause analysis to determine the root cause of channel performance degradation. The VNA / AI engine 350 can use unified channel scores calculated by RRM 334. The VNA / AI engine 350 can perform root cause analysis to determine the root cause of quality degradation of a given channel (e.g., due to interference observed by AP 142), such as improper placement of one or more APs, interference generated by devices within the site, suboptimal channel allocation, other metrics, etc. In one example, the VNA / AI engine 350 obtains metrics regarding channel interference processed by RRM 334. The VNA / AI engine 350 determines that the root cause of the channel interference is devices within site 102A generating non-WIFI interference.

[0086] The VNA / AI engine 350 can generate customer insights regarding the placement and configuration of AP 142 within site 102. The VNA / AI engine 350 can use information such as that used to perform root cause analysis to generate insights including: recommendations on changing the placement of AP 142, eliminating interference sources (e.g., interference sources such as other equipment, lights, machinery, etc.), changing the configuration of AP 142 (e.g., adjusting broadcast power, changing channel allocation, etc.), identifying a given site with a relatively high noise floor (e.g., a factory floor where interference may be unavoidable), and / or other insights. The VNA / AI engine 350 can generate an instance of user interface 310 as a visual indication including one or more insights, and cause the NMS 300 to output the instance of user interface 310.

[0087] RRM 334 can generate forecast channel scores that indicate the predicted future performance of one or more channels. RRM 334 can generate forecast channel scores based on one or more factors, such as in response to user-driven events (e.g., requests from administrators to generate forecast channel scores, requests to proactively determine future channel allocations, etc.), in response to upcoming scheduling events (e.g., upcoming configuration changes), due to anomalous events (e.g., unexpected changes in channel allocations, rapid deterioration of one or more metrics, etc.) and / or based on other factors. For example, RRM 334 can use forecast channel scores to determine channel allocations for the immediate next hour in response to local events (e.g., events associated with individual network devices), and to determine channel allocations for the next time period in response to global scheduling events (e.g., site-wide events, system level 100 events, etc.). RRM 334 can use forecast channel scores to proactively determine which channels are likely to perform relatively well in supporting users and which channels are unlikely to perform relatively well in supporting users at future points in time. RRM 334 can use forecast channel scores to replace and / or supplement other channel scores. For example, RRM 334 can use the predicted channel score as an additional input when determining channel allocation.

[0088] The RRM 334 can use one or more ML models 380 to generate predicted channel scores. The RRM 334 can provide historical data as input to the ML model 380 and receive the predicted channel scores as output. In one example, the RRM 334 determines that predicted channel scores should be calculated for the AP in response to a scheduling configuration change. The RRM 334 applies the model of the ML model 380 to the historical data, causing the ML model to output predicted channel scores. The ML model outputs predicted channel scores, and the RRM 334 uses these predicted channel scores to determine the channel allocation for the AP.

[0089] In some examples, RRM 334 can use information about anomalies when generating predicted channel scores. RRM 334 can obtain information about anomalies that lead to channel reallocation and feed this information as input to the ML model of ML model 380, receiving predicted channel scores as output from the ML model. RRM 334 can provide this information about anomalies when using ML model 380 to determine predicted channel scores to penalize channels with anomalies (e.g., reducing or otherwise negatively weighting predicted channel scores associated with channels experiencing a higher-than-average number of anomalies). In one example, RRM 334 obtains information about anomalies associated with a specific channel, where the anomalies cause periodic channel reallocation away from that channel. In addition to historical data associated with the specific channel, RRM 334 also feeds anomalies as input to the model of ML model 380. The ML model generates channel scores penalized based on the anomalies associated with the specific channel. RRM 334 uses these penalized channel scores to determine channel allocation.

[0090] In some examples, the RRM 334 can aggregate scores by channel to generate site-wide (or "site-level") channel scores. The RRM 334 can generate site-wide channel scores that represent channel quality (e.g., interference level) across the entire site, as opposed to the wireless environment of individual APs. The RRM 334 can aggregate channel scores for a given channel into a site-wide channel score to obtain a site view of which channels are optimal / problematic across all APs. For example, the RRM 334 can determine the site-level channel score for at least one channel based on the average of the channel scores of at least one channel across APs at a site.

[0091] In some examples, RRM 334 can aggregate scores by channel and AP to generate individual channel scores for one or more APs. RRM 334 can aggregate channel scores for one or more channels of an AP to generate individual channel scores indicating which channels are optimal / problematic for each AP within a site. RRM 334 can then use these individual channel scores to assign channels to individual APs within a site.

[0092] In some examples, RRM 334 can analyze APs that report high channel scores (e.g., scores above a threshold, or scores relatively higher than other APs). RRM 334 can analyze the APs and determine whether any of the APs is transmitting on a channel with a relevant channel score above the threshold. In one example, RRM 334 calculates a relatively high channel score for an AP. RRM 334 determines that the AP has been assigned a channel with a relatively high channel score and reconfigures the AP to transmit using a different channel with a relatively low channel score.

[0093] Figure 4 An example user equipment (UE) device 400 is shown. Figure 4 The example UE device 400 shown can be used to implement any of the UE 148 illustrated and described herein with reference to FIG. 1. The UE device 400 can include any type of wireless client device, and this disclosure is not limited thereto. For example, the UE device 400 can include mobile devices such as smartphones, tablets or laptops, personal digital assistants (PDAs), wireless terminals, smartwatches, smart rings, or any other type of mobile or wearable device. The UE 400 can also include any type of IoT client device, such as printers, security sensors or devices, environmental sensors, or any other connected device configured to communicate on one or more wireless networks.

[0094] UE device 400 includes a wired interface 430, wireless interfaces 420A-420C, one or more processors 406, memory 412, and user interface 410. Various components are coupled together via bus 414, allowing them to exchange data and information. The wired interface 430 includes a receiver 432 and a transmitter 434. If needed, the wired interface 430 can be used to couple UE 400 to the network(s) 104 of Figure 1. The first wireless interface 420A, second wireless interface 420B, and third wireless interface 420C each include receivers 422A, 422B, and 422C, respectively. Each receiver includes a receiving antenna, allowing UE 400 to receive data from wireless communication devices (such as AP 142 in Figure 1). Figure 2 The UE 400 can receive wireless signals from AP 200, other UE 148, or other devices configured to perform wireless communication. The first wireless interface 420A, the second wireless interface 420B, and the third wireless interface 420C further include transmitters 424A, 424B, and 424C, respectively. Each transmitter includes a transmitting antenna, through which the UE 400 can transmit signals to wireless communication devices (such as AP 142 in Figure 1, AP 200, other UE 148, or other devices configured to perform wireless communication). Figure 2The AP 200, other UEs 148, and / or other devices configured to conduct wireless communication transmit wireless signals. In some examples, the first wireless interface 420A may include a Wi-Fi 802.11 interface (e.g., 2.4 GHz and / or 5 GHz), and the second wireless interface 420B may include a Bluetooth interface and / or a Bluetooth Low Energy interface. The third wireless interface 420C may include, for example, a cellular interface, through which the UE device 400 can connect to a cellular network.

[0095] Multiple processors 406 execute software instructions (such as software instructions for defining software or computer programs) stored in a computer-readable storage medium (such as memory 412), such as a non-transitory computer-readable medium including storage devices (e.g., disk drives or optical disk drives) or memory (such as flash memory or RAM), or store instructions to cause one or more processors 406 to perform the techniques described herein, in any other type of volatile or non-volatile memory.

[0096] Memory 412 includes one or more devices configured to store programming modules and / or data associated with the operation of UE 400. For example, memory 412 may include computer-readable storage media, such as non-transitory computer-readable media, including storage devices (e.g., disk drives or optical disk drives) or memories (such as flash memory or RAM), or any other type of volatile or non-volatile memory that stores instructions to cause one or more processors 406 to perform the techniques described herein.

[0097] In this example, memory 412 includes an operating system 440, applications 442, a communication module 444, configuration settings 450, data storage for network data 454, and an agent 494. The data storage for network data 454 may include, for example, status / error logs, including UE 400-specific network data. As described above, network data 454 may include any network data, events, and / or status that may be relevant to determining one or more roaming quality assessments. Network data may include event data, such as logs of normal and error events based on log recording levels from a network management system (e.g., NMS 130 / 300). The data storage for network data 454 may store any data used and / or generated by the UE 400, such as network data used to determine proximity to proximity zones, which is collected by the UE 400 and sent to any AP 142 of the wireless network 106 for further transmission to the NMS 130.

[0098] The communication module 444 includes program code that, when executed by the processor(s) 406, enables the UE 400 to communicate using any of the wired interfaces 430, wireless interfaces 420A-420B, and / or cellular interfaces 450C. The configuration settings 450 include any device settings configured for the UE 400 for each of the wireless interfaces 420A-420B and / or cellular interfaces 420C.

[0099] Processor 406 can execute agent 494, which may be a software component of UE device 400, that captures data about one or more aspects of the performance of UE device 400. Agent 494 may capture information about the performance of one or more applications (e.g., the video conferencing application of application 442) and / or information about one or more SLEs associated with UE 400. For example, agent 494 may capture information about packets dropped during a video conferencing call and include that information in data 454.

[0100] Figure 5 This is a block diagram illustrating an example network node 500 configured according to the techniques described herein. In one or more examples, network node 500 implements attachment to... Figure 1A / Figure 1B The network devices or servers 104 include, for example, routers, switches, AAA servers 110, DHCP servers 116, DNS servers 122, VNAs 132, AP location modules 135, web servers 128A-128X, etc., or network devices such as routers and switches.

[0101] In this example, network node 500 includes a communication interface 502 (e.g., an Ethernet interface), a processor 506, input / output 508 (e.g., a display, buttons, keyboard, keypad, touchscreen, mouse, etc.), memory 512, and an assembly of components 516 (e.g., an assembly of hardware modules, such as circuitry) coupled together via bus 509. These various components can exchange data and information on bus 509. Communication interface 502 couples network node 500 to a network, such as an enterprise network.

[0102] Although only one interface is shown as an example, those skilled in the art will recognize that a network node may also have multiple communication interfaces. Communication interface 502 includes a receiver 520 through which network node 500 can receive data and information (e.g., data indicating distance between APs, and / or operational information such as registration requests, AAA services, DHCP requests, Simple Notification Service (SNS) lookups, and web page requests). Communication interface 502 also includes a transmitter 522 through which network node 500 can transmit data and information (e.g., location information, configuration information, authentication information, web page data, etc.).

[0103] Memory 512 stores executable software applications 532, operating system 540, and data / information 530. Data 530 includes system logs and / or error logs, which store network data and / or proximity information of node 500 and / or other devices (such as wireless access points) based on logging levels according to instructions from the network management system. In some examples, network node 500 may forward network data to the network management system (e.g., NMS130 of Figure 1) for the analysis described herein.

[0104] Figures 6A to 6B These are example indicator graphs 600A and 600B of wireless channels according to one or more technologies of this disclosure. Figures 6A to 6B Is Figure 1A Described in the context of.

[0105] exist Figure 6A In the example, NMS 130 obtains data from an AP (such as AP 142A-1) including one or more metrics for a single channel. NMS 130 can obtain metrics regarding non-Wi-Fi interference, noise floor, undecodeable Wi-Fi interference, unknown Wi-Fi interference, and / or other metrics. NMS 130 can obtain metrics from the AP multiple times (e.g., by...). Figure 6A The data represents the metrics indicated by the timestamps shown.

[0106] The NMS 130 can process the acquired metrics to calculate normalized metrics for the channel. The NMS 130 can calculate normalized metrics including "Non-WIFI Score" (e.g., Non-WIFI 614A, interference from sources different from WIFI devices, such as weather radar), "Noise Basis Score" (e.g., Noise Basis Score 612A, the minimum amount of noise recorded on the wireless channel in dBm over a time period), "Undecipherable WIFI Score" (e.g., Undecipherable WIFI Score 606A, WIFI interference from hidden networks), and "Unknown WIFI Score" (e.g., Unknown WIFI Score 608A, interference caused by unknown devices). As part of the score processing, the RRM 134 can normalize the values ​​observed on a given channel at a given time. The RRM 134 can normalize the value of each metric to a value between 0 and 1, representing channel quality. The RRM 134 can normalize the metric to produce a score for each metric in a row. If the normalized value is close to 0, RRM 134 determines that the observed value is normal and optimal for performance. If the normalized value is close to 1, RRM 134 determines that the observed value is anomalous and bad for performance.

[0107] The RRM 134 can calculate product scores (e.g., product score 604, "row score (product)") and / or linearly weighted scores (e.g., linearly weighted score 610A, "row score (linearly weighted)") as a unified channel score representing the quality of the channel. The RRM 134 can calculate product score 604A to ensure that the unified channel score reflects the channel quality and that no individual types of interference are lost in the unified channel score. Figure 6A In the example, RRM 134 calculates the product score 604A as relatively higher after 21:00 compared to the linear weighted score 610A (e.g., 0.6 vs. 0.1 near 21:00) to account for the relatively high undecodeable WIFI score 606A at 21:00.

[0108] The NMS 130 can generate graph 600A to visually display the product score 604A, the linearly weighted score 610A, and the metrics 606A, 608A, 612A, and 614A. The NMS 130 can generate graph 600A to visually indicate the scores and metrics associated with the channel and output graph 600A to the administrator. For example, the NMS 130 can generate graph 600A to provide the administrator with a visual indication of the channel's performance.

[0109] exist Figure 6B In the example, RRM 134 generates and Figure 6AThe curve 600A is exactly the same as curve 600B, except that the metrics for channels that differ from the unified channel score have been removed. For example... Figure 6B As shown, RRM 134 generates product scores 604B and linear weighted scores 610B with significantly different values ​​(e.g., between 0 and 3:00, and starting from 15:00). RRM 134 can use product scores instead of linear weighted scores to avoid assigning channels with relatively low scores for some types of interference over relatively high scores for others (e.g., in cases where one type of interference might render a channel unusable, but other types of interference have relatively low scores and also result in relatively low linear weighted scores). Although shown as including linear weighted scores for comparative purposes (e.g., to illustrate the difference between product and linear weighted unified channel scores), RRM 134 can also suppress the calculation of linear weighted scores and can use product scores when determining channel allocations.

[0110] Figure 7 It is a collection of graphs 760 of example indicators of wireless channels according to one or more technologies of this disclosure. Figure 7 Is Figure 1A Described in the context of.

[0111] RRM 134 can generate with Figures 6A to 6B One or more similar graphs are shown. For example, the RRM 134 can... Figure 7 The curve is generated as including and Figures 6A to 6B The diagram shows similar curves for multiple channels at a site. (Example) Figure 7 As shown, RRM 134 can generate a graph 760 for each channel in the frequency band, including normalized values ​​of interference and a unified channel score. RRM 134 can generate... Figure 7 The graph provides administrators with a view of the performance of one or more channels over time.

[0112] Figure 8 It is a collection of graphs 862 of example indicators including prediction indicators of wireless channels within a wireless band, based on one or more techniques of this disclosure. Figure 8 Is Figure 1A Described in the context of.

[0113] RRM 134 can generate graph 862 as an indication including the forecast channel score (e.g., Figure 8The “Channel Score (Prediction)” is shown. RRM 134 can generate each graph 862 as a visual representation of an indicator of the relevant channel, such as the predicted channel score. RRM 134 can determine the predicted channel and generate graph 862 including a predicted channel score indication 864 (e.g., a diamond indicator visually displayed within each graph of graph 862). Figure 8 In the example, RRM 134 generates graph 862 to include a predicted channel score indication 864 in addition to indications of other scores, including channel score, scan noise floor score, unknown WIFI score, radar score, scan scores of receivers from other base stations (“scan RXOTHERBSS score”), and undecodeable WIFI score. In other examples, RRM 134 may generate graph 862 to visually include the predicted channel score using different indications of more or fewer other scores and / or metrics.

[0114] Figure 9 This is a flowchart illustrating an example operation for determining channel allocation based on one or more techniques disclosed herein. Figure 9 Is Figure 1A Described in the context of.

[0115] A network management system (such as NMS 130) acquires data (902) associated with at least one of multiple channels in a frequency band at a site (such as site 102A). NMS 130 may acquire data including a set of indicators (such as non-WIFI indicators, undecodeable WIFI indicators, unknown WIFI indicators, noise floor indicators, and / or other indicators). NMS 130 may acquire data based on interference observed by the AP's continuous scanning radio and / or data radio.

[0116] The NMS 130 calculates a normalized metric (904) for each metric in the set of observed metrics for at least one channel relative to a threshold representing the degraded performance of the at least one channel. The NMS 130 can calculate a normalized metric representing the quality of at least one channel relative to the corresponding metric. For example, the NMS 130 can normalize each metric to a value between 1 and 0, where 1 represents relatively poor or abnormal performance and 0 represents relatively good performance.

[0117] The NMS 130 calculates a channel score (906) for at least one channel based on the product of normalized indices from a set of indices observed for at least one channel. The NMS 130 can calculate the channel score as an indication of the quality of at least one channel relative to the set of indices. For example, the NMS 130 can calculate a uniform channel score using values ​​between 1 and 0, where 1 indicates relatively poor or anomalous performance of the channel, and 0 indicates relatively good performance of the channel.

[0118] The NMS 130 assigns a channel to at least one of multiple APs (such as AP 142A-1) at site 102 based on the channel score. The NMS 130 can use the channel score to determine whether to suppress the assignment of a channel to an AP, reassign an AP from that channel to a different channel, and / or retain the AP assigned to the channel. For example, the NMS 130 can determine that a given AP should be reassigned from the first channel to a second channel based on the fact that the first channel has a relatively high channel score.

[0119] The techniques described herein can be implemented in hardware, software, firmware, or any combination thereof. Various features described as modules, units, or components can be implemented together in an integrated logic device or separately as discrete but interoperable logic devices or other hardware devices. In some cases, various features of an electronic circuit system can be implemented as one or more integrated circuit devices, such as integrated circuit chips or chipsets.

[0120] If implemented in hardware, this disclosure is applicable to devices such as processors or integrated circuit devices (e.g., integrated circuit chips or chipsets). Alternatively or additionally, if implemented in software or firmware, the technology can be implemented at least in part by a computer-readable data storage medium including instructions that, when executed, cause a processor to perform one or more of the methods described above. For example, a computer-readable data storage medium may store such instructions for execution by a processor.

[0121] Computer-readable media can form part of a computer program product, which may include packaging material. Computer-readable media may include computer data storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile random-access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage media, etc. In some examples, the article of manufacture may include one or more computer-readable storage media.

[0122] In some examples, computer-readable storage media may include non-transitory media. The term "non-transitory" can indicate that the storage medium is not embodied in a carrier wave or propagating signal. In some examples, non-transitory storage media may (e.g., in RAM or cache) store data that may change over time.

[0123] The code or instructions can be software and / or firmware executed by a processing circuitry system comprising one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other equivalent integrated or discrete logic circuitry systems. Accordingly, the term "processor" as used herein can refer to any of the foregoing structures or any other structure suitable for implementing the techniques described herein. Furthermore, in some aspects, the functionality described in this disclosure can be provided within a software module or a hardware module.

Claims

1. A network management system (NMS), comprising: Memory; as well as A processing circuitry system that communicates with the memory and is configured to: Obtain data associated with at least one of a plurality of channels in a frequency band at the site, wherein the data includes a set of indicators; Calculate a normalized metric for each metric in the set of metrics observed for the at least one channel relative to a threshold representing the degradation performance of the at least one channel, wherein the normalized metric represents the quality of the at least one channel relative to the corresponding metric; A channel score is calculated for the at least one channel based on the product of the normalized indices of the set of indices observed for the at least one channel, wherein the channel score represents the quality of the at least one channel relative to the set of indices. as well as Based on the channel score for the channel, the channel is assigned to at least one of a plurality of access point APs at the site.

2. The NMS of claim 1, wherein, in order to allocate the channel, the processing circuitry is further configured to: allocate the channel to the at least one AP for a subsequent time window based on one or more channel scores for the channel in a previous time window.

3. The NMS of claim 1, wherein the data includes interference data observed at each of the plurality of APs at the site for the at least one channel, and wherein, in order to obtain the interference data, the processing circuitry is configured to obtain the interference data for the at least one channel from a continuous scanning radio of one or more of the plurality of APs.

4. The NMS of claim 1, wherein, in order to obtain the data, the processing circuitry is configured to obtain the data from two or more of the following: Continuous scanning of radio readings, Data radio readings, Access points or network access devices not managed by the NMS, Radar system, Third-party application data, Automatic Frequency Coordination (AFC) system, Electronic shelf label (ESL) system, and / or Fast Fourier Transform (FFT) dynamic scanning or RF spectrum capture.

5. The NMS according to any one of claims 1-4, wherein each of the normalized index and the channel score includes a value between 0 and 1, where 0 represents normal quality of the channel and 1 represents poor quality of the channel.

6. The NMS according to any one of claims 1-4, wherein, in order to obtain the data, the processing circuitry is configured to: obtain the data from continuous scanning radio waves of one or more of the plurality of APs at the site, and wherein the set of metrics includes: Non-WIFI indicators Noise floor index Undecipherable Wi-Fi indicator, and Unknown Wi-Fi indicator.

7. The NMS according to any one of claims 1-4, wherein the processing circuitry is configured to: determine a site-level channel score for the at least one channel based on the average of the channel scores of the plurality of APs across the site.

8. The NMS according to any one of claims 1-4, wherein the processing circuitry is further configured to perform root cause analysis to determine the root cause of the degradation performance of the at least one channel.

9. The NMS according to any one of claims 1-4, wherein the data includes Service Level Experience (SLE) data associated with a client device connected to one or more of the plurality of APs, and wherein, in order to obtain the SLE data, the processing circuitry is configured to calculate the SLE data based on network data obtained from at least one of the one or more APs of the plurality of APs.

10. The NMS according to any one of claims 1-4, The data associated with the at least one channel includes historical data. The processing circuitry is further configured to: use at least one machine learning model to generate a predicted channel score for the at least one channel, the predicted channel score indicating the predicted future performance of the at least one channel, and In order to allocate the channel, the processing circuitry is further configured to allocate the channel to at least one of the plurality of APs based on the predicted channel score.

11. A computer networking method, comprising: Data associated with at least one of a plurality of channels in a frequency band at a site is obtained by the network management system (NMS), wherein the data includes a set of indicators; The NMS calculates a normalized metric for each metric in the set of metrics observed for the at least one channel relative to a threshold representing the degradation performance of the at least one channel, wherein the normalized metric represents the quality of the at least one channel relative to the corresponding metric. The NMS calculates a channel score for the at least one channel based on the product of normalized indices of the set of indices observed for the at least one channel, wherein the channel score represents the quality of the at least one channel relative to the set of indices. as well as The NMS assigns the channel to at least one of a plurality of access point APs at the site based on the channel score for the channel.

12. The computer networking method of claim 11, wherein assigning the channel further comprises: Based on one or more channel scores for the channel in a previous time window, the channel is assigned to the at least one AP for use in a subsequent time window.

13. The computer networking method of claim 11, wherein the data comprises interference data observed at each of the plurality of APs at the site for the at least one channel, and wherein obtaining the interference data comprises: The interference data for the at least one channel is obtained from the continuous scanning radio of one or more of the plurality of APs.

14. The computer networking method of claim 11, wherein obtaining the data further comprises obtaining the data from two or more of the following: Continuous scanning of radio readings, Data radio readings, Access points or network access devices not managed by the NMS, Radar system, Third-party application data, Automatic Frequency Coordination (AFC) system, Electronic shelf label (ESL) system, and / or Fast Fourier Transform (FFT) dynamic scanning or RF spectrum capture.

15. The computer networking method according to any one of claims 11-14, wherein each of the normalization index and the channel score includes a value between 0 and 1, wherein 0 represents normal quality of the channel and 1 represents poor quality of the channel.

16. The computer networking method of any of claims 11-14, wherein obtaining the data further comprises: The data is obtained from continuous scanning radio waves from one or more of the plurality of APs at the site, and the set of indicators includes: Non-WIFI indicators Noise floor index Undecipherable Wi-Fi indicator, and Unknown Wi-Fi indicator.

17. The computer networking method according to any one of claims 11-14, further comprising: The NMS determines the site-level channel score for the at least one channel based on the average of the channel scores of the plurality of APs across the site.

18. The computer networking method of any of claims 11-14, further comprising: The NMS performs a root cause analysis to determine the root cause of the degraded performance of the at least one channel.

19. The computer networking method of any of claims 11-14, wherein the data comprises service level experience (SLE) data associated with client devices connected to one or more of the plurality of APs, and wherein obtaining the SLE data comprises: The SLE data is calculated based on network data obtained from at least one of the multiple APs.

20. A computer-readable storage medium encoded with instructions for configuring one or more programmable processors to perform an NMS according to any one of claims 1-10, or to perform a method according to any one of claims 11-19.

Images