Joint management of overlapping wireless networks

Abstract

This disclosure relates to the joint management of overlapping wireless networks. This disclosure describes techniques for managing multiple wireless networks providing overlapping coverage to user equipment. In one embodiment, this disclosure describes a computing system configured to: collect network data associated with a first wireless network; collect network data associated with a second wireless network, wherein the first and second wireless networks have overlapping coverage areas, and wherein the first and second wireless networks are different wireless network types; identify user equipment attached to the first wireless network and located in the overlapping coverage area based on the network data associated with the first wireless network, wherein the user equipment can also be attached to the second wireless network; and predict network conditions affecting the user equipment based on both the network data associated with the first wireless network and the network data associated with the second wireless network.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit of U.S. Patent Application No. 19 / 042,741, filed January 31, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to computing networking, and more specifically to the management of wireless networks. Background Technology

[0004] Computer networks have become ubiquitous, and the number and types of network applications, connected devices, and connected devices are rapidly expanding. Private cellular networks, such as private 5G networks, can be used by organizations that need secure, high-performance, low-latency networks tailored for mission-critical applications. Such private cellular networks can support industries including manufacturing, healthcare, and automation, where real-time data processing and scalability are critical. Local wireless networks, such as Wi-Fi, provide cost-effective, user-friendly wireless connectivity with fast, broad compatibility, and scalability. These local wireless networks often work well in indoor environments and for IoT devices. Summary of the Invention

[0005] This disclosure describes techniques for managing multiple wireless networks that provide overlapping coverage to user equipment. The techniques described herein involve collecting performance metrics, key performance indicators, and other information from multiple different types of networks, such as cellular mobile networks and Wi-Fi networks. The management system uses the collected information to perform joint management operations for the networks and / or user equipment attached to any of the networks.

[0006] In some embodiments, an artificial intelligence or machine learning model is trained to identify various conditions across multiple wireless networks, such as network congestion associated with one or more networks, anomalous data usage, abnormal user equipment attachment, and / or other conditions. Such a model may be based on historical information collected from the monitored network or from other networks. The federated management system can apply this model to the operating wireless networks to identify network conditions, such as congestion or anomalous activity, and propose actions to remediate those conditions. Such actions can be executed automatically or after administrator authorization. By leveraging insights gained from metrics collected across multiple wireless networks, the federated management system can manage a collection of networks more effectively than a system managing multiple networks individually.

[0007] In some embodiments, this disclosure describes operations performed by a computing system according to one or more aspects of this disclosure. In one particular embodiment, this disclosure describes a method comprising: collecting network data associated with a first wireless network by a computing system; collecting network data associated with a second wireless network by a computing system, wherein the first and second wireless networks have overlapping coverage areas, and wherein the first and second wireless networks are different wireless network types; identifying user devices attached to the first wireless network and located in the overlapping coverage area based on the network data associated with the first wireless network, wherein these user devices are also capable of attaching to the second wireless network; predicting network conditions affecting the user devices based on both the network data associated with the first wireless network and the network data associated with the second wireless network; and performing actions to remedy the network conditions affecting the user devices based on the predicted network conditions affecting the user devices by the computing system.

[0008] In another embodiment, this disclosure describes a system including a storage system and processing circuitry capable of accessing the storage system, wherein the processing circuitry is configured to: collect network data associated with a first wireless network; collect network data associated with a second wireless network, wherein the first and second wireless networks have overlapping coverage areas and wherein the first and second wireless networks are different wireless network types; identify user devices attached to the first wireless network and located in the overlapping coverage area based on the network data associated with the first wireless network, wherein these user devices are also capable of attaching to the second wireless network; predict network conditions affecting the user devices based on both the network data associated with the first wireless network and the network data associated with the second wireless network; and perform actions to remedy the network conditions affecting the user devices based on the predicted network conditions affecting the user devices.

[0009] In another embodiment, this disclosure describes a computer-readable storage medium including instructions that, when executed, configure processing circuitry of a computing system to: collect network data associated with a first wireless network; collect network data associated with a second wireless network, wherein the first and second wireless networks have overlapping coverage areas and wherein the first and second wireless networks are different wireless network types; identify, based on the network data associated with the first wireless network, a user device attached to the first wireless network and located in the overlapping coverage area, wherein the user device is also capable of attaching to the second wireless network; predict network conditions affecting the user device based on both the network data associated with the first wireless network and the network data associated with the second wireless network; and perform actions to remedy the network conditions affecting the user device based on the predicted network conditions affecting the user device.

[0010] This overview is intended to provide a brief summary of some of the topics described in this document. Therefore, the features described above are merely embodiments and should not be construed as limiting the scope or spirit of this disclosure. Other features, objects, and advantages of this disclosure will be apparent from the specification and drawings, as well as from the claims. Attached Figure Description

[0011] Figure 1 This is a conceptual diagram illustrating an example network system for managing multiple wireless networks that provide overlapping coverage to wireless devices, according to one or more technologies of this disclosure.

[0012] Figure 2 This is a conceptual diagram of a block diagram of a computing system configured to manage multiple wireless networks providing overlapping coverage to wireless devices, based on one or more technologies of this disclosure.

[0013] Figure 3A , Figure 3B , Figure 3C , Figure 3D and Figure 3E This is a conceptual diagram illustrating an example user interface presented by a user interface device according to one or more aspects of this disclosure.

[0014] Figure 4A and Figure 4B This is a conceptual diagram illustrating another example user interface presented by a user interface device according to one or more aspects of this disclosure.

[0015] Figure 5 This is a flowchart illustrating operations performed by an example joint operations manager in accordance with one or more aspects of this disclosure.

[0016] While each of the foregoing figures has been referenced in connection with one or more specific embodiments herein, such embodiments are merely illustrative, and each illustration may be used to provide support for other embodiments not specifically described herein. Therefore, the embodiments described herein with reference to any of the foregoing figures should not be construed as limiting the scope or spirit of the subject matter shown or otherwise disclosed herein. Detailed Implementation

[0017] Wi-Fi networks are ubiquitous in enterprise environments, providing wireless coverage for user devices and equipment. Private cellular networks (e.g., 5G and / or xG networks) can also be deployed in the same enterprise environment, providing overlapping wireless coverage for the same or similar set of wireless devices. However, private cellular networks are often managed by separate management components that may conflict with the tools used to manage Wi-Fi networks. This disclosure describes techniques for the joint and coordinated management of multiple wireless networks, including private cellular networks and Wi-Fi networks.

[0018] Managing and monitoring both private cellular and Wi-Fi networks is becoming increasingly complex, as these networks serve numerous devices. A key challenge in managing and monitoring these networks lies in Root Cause Analysis (RCA), a crucial aspect of troubleshooting private mobile networks and Wi-Fi. Network engineers must hypothesize, test, and confirm the nature of problems before they can resolve them. However, tools that tend to overwhelm users with numerous alerts and other information instead of clearly identifying the issue may require network engineers and support teams to manually perform complex calculations to resolve these problems.

[0019] At least some of the technologies described in this paper address these challenges by leveraging artificial intelligence techniques and machine learning algorithms to provide unified network monitoring across both private cellular networks (e.g., private 5G) and local wireless networks (e.g., Wi-Fi).

[0020] Figure 1 This is a conceptual diagram illustrating an example network system 100 according to one or more techniques of this disclosure, in which multiple wireless networks providing overlapping coverage to wireless devices are managed. The techniques described herein are primarily applicable to environments with two or more wireless networks, especially when these networks are of different types, such as in environments where both 5G cellular mobile networks and Wi-Fi networks provide overlapping wireless coverage to the same geographic area.

[0021] exist Figure 1In this embodiment, cellular network 120 is a cellular mobile network, such as a 5G or xG mobile network providing wireless connectivity to any number of user equipments 104A to 104N (“User Equipment 104” or “User Device 104”). Cellular network 120 includes a radio access network 109 and a mobile core network 105. Figure 1 In this context, cellular network 120 can cover a coverage area defined by the range of one or more base stations 106. Cellular network 120 is primarily described herein as a private cellular network operated by an organization to benefit its employees, users, or members; however, the techniques described herein can be applied to cellular networks in other contexts.

[0022] Local wireless network 130 is also a wireless network providing wireless connectivity to user equipment 104, such as a network conforming to one or more of the IEEE 802.11 standards (i.e., "Wi-Fi"). As a Wi-Fi network, local wireless network 130 is typically characterized by one or more access points 131, which, in at least some implementations, may cover a smaller geographic area than the geographic area covered by a cellular network base station. Local wireless network 130 is primarily described herein as a Wi-Fi network, but it can also be another type of wireless network, such as a network based on Bluetooth / Bluetooth Low Energy (BLE) protocols, mesh networking protocols such as ZigBee, or other wireless network technologies. Furthermore, although primarily described herein as a "local" wireless network, the service area of ​​local wireless network 130 does not need to be strictly "local," but such a service area may be very large and, in some cases, may exceed the service area of ​​cellular network 120 and / or the typical coverage area of ​​a Wi-Fi network.

[0023] User equipment 104 may represent a smartphone, desktop computer, laptop computer, tablet computer, smartwatch, and / or "Internet of Things" (IoT) device (such as a camera, sensor, television, appliance, etc.). Some user equipment 104 may only have cellular network communication capabilities, enabling such user equipment 104 to attach to and / or communicate with cellular network 120, rather than local wireless network 130. Other user equipment 104 may only have wireless network or Wi-Fi communication capabilities, enabling such user equipment 104 to attach to and / or communicate with local wireless network 130, rather than cellular network 120. However, in many cases, user equipment 104 may have both cellular network communication capabilities and wireless network communication capabilities, enabling such user equipment 104 to attach to or communicate with either cellular network 120 or local wireless network 130.

[0024] Therefore, both cellular network 120 and local wireless network 130 can provide access to one or more of user equipment 104A to 104N to one or more applications or services provided by network 115. Network 115 can represent, for example, one or more service provider networks and services, the Internet, another private network, a network that provides access to third-party services, one or more IP-VPNs, IP-Multimedia Subsystems, combinations thereof, or any other network or combination of networks.

[0025] Cellular network 120 includes one or more radio access networks 109 and one or more mobile core networks 105. Radio access networks 109 provide network access, data transmission, and other services to user equipment 104. In some embodiments, radio access networks (or “RANs”) 109 may be open radio access networks (O-RANs), 5G mobile network RANs, 4G LTE mobile network RANs, another type of RAN, or a combination of these networks. For example, in a 5G-RAN, each radio access network 109 includes multiple cell sites (or simply “cells”), each cell site including radio devices (such as base station 106, also called gNodeBs) to exchange packet data within the data network, thereby ultimately accessing one or more applications or services provided by data network 115.

[0026] Each component in base station 106 can be divided into three functional components: Radio Unit (RU), Distributed Unit (DU), and Central Unit (CU), which can be deployed in various configurations. The RU manages the radio frequency layer and has antenna arrays of various sizes and shapes. The DU performs lower-layer protocol processing. The CU performs upper-layer protocol processing. Depending on operator and service requirements, base station 106 can be deployed monolithically; for example, the RU, DU, and CU may reside within a cell site, or these functions may be distributed across cell sites, with the CU residing in an edge cloud site controlling multiple distributed DUs. For example, O-RAN is a networking approach where separated functions can be used to deploy mobile front-end transmission and intermediate transmission networks. These separated functions can be cloud-based.

[0027] Mobile core network 105 may be a 5G core network, and network 115 may represent, for example, one or more service provider networks and services, the Internet, third-party services, one or more IP-VPNs, IP-Multimedia Subsystems, combinations thereof, or other networks or combinations of networks. In some embodiments, resources associated with services provided to tenants by a mobile network operator may be provided or managed by the functions of mobile core network 105 and / or components of radio access network 109. Mobile core network 105 may implement various discrete control plane and user plane functions of network system 100. Further details regarding such control plane and user plane functions can be found in U.S. Patent Application No. 18 / 620,733, filed March 28, 2024, entitled “Service Management and Orchestration For Private and Public Mobile Networks” (Attorney General’s Reference 2014-676US01), which is incorporated herein by reference.

[0028] Local wireless network 130 Figure 1 The diagram shows a Wi-Fi network including a Wi-Fi manager 132 and one or more access points 131. The Wi-Fi manager 132 can perform operations related to the management of the local wireless network 130, including the coordination of access points 131 and other hardware of the local wireless network 130. In some embodiments, some or all of the functions performed by the Wi-Fi manager 132 may be performed by one or more access points 131. Each of the access points 131 may be a commercial or enterprise access point, a router, or any other device capable of providing wireless network access. The access points 131 are capable of wirelessly connecting user equipment 104 to the local wireless network 130 using various wireless network protocols and technologies, such as one or more wireless LAN protocols conforming to the IEEE 802.11 standard (i.e., "Wi-Fi"), Bluetooth / Bluetooth Low Energy (BLE), mesh networking protocols such as ZigBee, or other wireless network technologies.

[0029] The local wireless network 130 may also encompass an organizational or enterprise network 135, which may include physical systems occupying some of the same physical space or sites available on the local wireless network 130. The enterprise network 135 may include systems and other network resources 136 that provide services used by or otherwise facilitate the tasks of the organization or enterprise (e.g., hospitals, airports, hotels, stadiums, retail stores, businesses, etc.). Figure 1As shown, one or more network resources 136 may include systems physically residing on sites served by the local wireless network 130 (i.e., included within the local wireless network 130), and one or more network resources 136 associated with the enterprise network 135 may be outside the local wireless network 130, such as... Figure 1 As shown (e.g., remotely accessible via another network). In some embodiments, particularly when cellular network 120 is a private mobile cellular network, cellular network 120 may also cover enterprise network 135 and provide access to such network resources 136 of enterprise network 135.

[0030] The techniques described herein can be applied to the management of networks such as cellular networks 120 and local wireless networks 130, which provide at least some degree of overlapping wireless coverage (e.g., by...). Figure 1 Overlapping wireless coverage (represented by 110 in the text). For ease of explanation, in Figure 1 The overlapping wireless coverage 110 indicated in the diagram represents a partial overlap between cellular network 120 and local wireless network 130. However, it should be understood that in many embodiments, this overlap may be more significant. For example, wireless coverage provided by one network (e.g., cellular network 120) may completely cover wireless coverage provided by another network (e.g., local wireless network 130), or vice versa.

[0031] The Joint Operations Manager 140 is a system for managing the cellular network 120 and the local wireless network 130. The Joint Operations Manager 140 can be implemented using any suitable computing system, including one or more server computers, workstations, appliances, cloud computing systems, mainframes, and / or other computing devices capable of performing the operations and / or functions described in one or more aspects of this disclosure. In other embodiments, such a computing system may represent or be implemented through one or more virtualized computing instances (e.g., virtual machines, containers) of a data center, cloud computing system, server farm, and / or server cluster.

[0032] Although Figure 1 The diagram shows a Joint Operations Manager 140 logically or physically separated from (and communicating with) cellular network 120 and local wireless network 130, but in other embodiments, the Joint Operations Manager 140 may be part of cellular network 120 or local wireless network 130. In other embodiments, the Joint Operations Manager 140 may also be... Figure 1 Another method not specifically shown in the document is to access the cellular network 120 and / or the local wireless network 130 (or resources on these networks) and / or interact with the cellular network 120 and / or the local wireless network 130 (or resources on these networks).

[0033] In operation, and according to one or more aspects of this disclosure, the joint operations manager 140 may collect information about the cellular network 120 and the local wireless network 130. For example, it may be possible to... Figure 1 In the embodiment described in the context of the above, the Joint Operations Manager 140 outputs a series of signals via network 115. Components within both the Cellular Network 120 and the Local Wireless Network 130 detect at least some of the signals and determine that these signals include a request 101 seeking information about the operation of each respective network. Devices and components associated with the Cellular Network 120 (e.g., Radio Access Network 109 and / or Mobile Core Network 105) respond to request 101 by outputting network data 102 to the Joint Operations Manager 140 via network 115. Similarly, devices and components associated with the Local Wireless Network 130 (e.g., Access Point 131 and / or Wi-Fi Manager 132) respond to request 101 by outputting network data 103 to the Joint Operations Manager 140 via network 115. The Joint Operations Manager 140 receives both network data 102 and network data 103, and determines that this data includes (or uses this data to derive) various performance metrics, key performance indicators, and other information about the operation of both cellular network 120 and local wireless network 130.

[0034] Despite Figure 1 In this embodiment, network data 102 and network data 103 are described as being sent to the Joint Operations Manager 140 in response to a request 101 initiated by the Joint Operations Manager 140. However, in other embodiments, network data 102 and 103 may be sent to the Joint Operations Manager 140 without first receiving a specific request 101. For example, elements or element management systems of the radio access network 109, mobile core network 105, and / or cellular network 120 may occasionally, periodically, or continuously send at least some network data 102 to the Joint Operations Manager 140 without first receiving a request 101 for such data. Furthermore, one or more access points 131 may occasionally, periodically, or continuously send at least some network data 103 to the Joint Operations Manager 140 without first receiving a request 101 for such data. Similarly, other elements of the local wireless network 130 (including Wi-Fi manager 132 or network resources 136) may occasionally, periodically, or continuously send at least some network data 103 to the Joint Operations Manager 140 without first receiving a request 101 for such data.

[0035] The Joint Operations Manager 140 can predict network congestion affecting one or more of the user equipment 104. For example, still referring to... Figure 1In the embodiments described in the context of [the previous sentence], the Joint Operations Manager 140 evaluates network data 102 and 103 and determines whether the local wireless network 130 is congested or expected to be congested when the cellular network 120 is not congested. To make this determination, the Joint Operations Manager 140 may apply one or more machine learning models trained to identify actual or expected network congestion. Such models may have been trained using data similar to network data 102 and 103, so that when the Joint Operations Manager 140 applies the model to network data 102 and 103, the model can generate an appropriate prediction about network congestion. In some embodiments, the Joint Operations Manager 140 may generate [the following information] for use by an administrator ([the administrator]). Figure 1 One or more user interfaces 300 (not shown) are presented at a computing device running to report congestion associated with the local wireless network 130.

[0036] The Joint Operations Manager 140 can perform operations to resolve or remedy network congestion associated with the local wireless network 130. For example, refer again... Figure 1 The Joint Operations Manager 140 evaluates options for resolving congestion in the local wireless network 130, including moving some of the user equipment 104 from the local wireless network 130 to the cellular network 120. The Joint Operations Manager 140 identifies one or more user equipment 104 connected to (or attached to) the local wireless network 130 but also capable of being attached to the cellular network 120. The Joint Operations Manager 140 selects one or more such user equipment 104 and detaches them from the local wireless network 130, enabling these same user equipment 104 to subsequently be attached to the cellular network 120. By moving one or more user equipment 104 from the local wireless network 130 to the cellular network 120, the Joint Operations Manager 140 can resolve the congestion associated with the local wireless network 130.

[0037] The techniques described in this paper offer several advantages. For example, by jointly managing multiple wireless networks, insights gained from metrics and other information collected across these networks can be leveraged more effectively than managing a collection of networks individually. Furthermore, jointly managing multiple wireless networks also allows for monitoring the overall quality of experience for individual devices roaming between multiple networks (e.g., aggregated data usage on cellular and local networks). Moreover, some of the techniques described address the challenges of managing private cellular and Wi-Fi networks by utilizing artificial intelligence and machine learning algorithms to provide unified network monitoring across both types of networks. By enabling timely or near real-time insights into network performance, automating root cause analysis, and recommending corrective actions, problems can be resolved more quickly.

[0038] Moreover, the techniques described and illustrated in this article are effective at highlighting root causes and recommending or performing specific actions to optimize the network, rather than overwhelming network administrators or users with massive amounts of data. These techniques not only reduce the complexity of managing large-scale enterprise networks but also minimize downtime and improve operational efficiency in relevant environments and contexts, enabling an organization's IT staff to focus on more strategic tasks.

[0039] Figure 2 This is a conceptual block diagram of a computing system comprising multiple wireless networks configured to manage overlapping coverage for opposing wireless devices, based on one or more technologies of this disclosure. Figure 2 System 200 includes combining Figure 1 The system 100 described has many of the same components. Figure 2 The elements shown may correspond to previously described elements that share the same reference numerals.

[0040] Figure 2 Also shown is a service and management orchestrator 112 (“SMO 112”), which includes a RAN intelligent controller (“RIC”) to manage aspects of the radio access network 109 and / or the mobile core network 105. Figure 2 In the illustrated embodiment, the RIC included within the service and management orchestrator 112 is a non-real-time RAN intelligent controller 122. Figure 2 The image also shows a near real-time RIC124.

[0041] Typically, a network system (such as network system 100) may include a service management and orchestration framework (e.g., implemented by a service management orchestrator 112), which, together with a non-real-time RIC (e.g., non-real-time RIC 122) configured according to the Open Radio Access Network (O-RAN) standard (“O-RAN Architecture”), provides various framework functions to manage and / or monitor aspects of the RAN and / or the 5G core. The O-RAN Architecture may include non-real-time RIC 122 and near-real-time RIC 124; each performing different functions and services for RAN functions. The non-real-time RIC is an orchestration and automation function configured to provide radio resource management, higher-level process optimization, policy optimization, and to provide guidance, parameters, policies, and artificial intelligence (AI) and machine learning (ML) models to support the operation of near-real-time RIC functions within the RAN. Non-real-time RICs can carry one or more applications (e.g., rApp) that provide non-real-time (e.g., greater than one second) control over RAN elements and their resources, while near-real-time RICs can carry one or more applications (e.g., xApp) that provide near-real-time control over RAN elements and their resources.

[0042] In some embodiments, the service and management orchestrator 112, the non-real-time RIC 122, and the near-real-time RIC 124 can be operated by a mobile network operator providing 5G services to tenants. The service and management orchestrator 112 can orchestrate and control the management and automation aspects of the radio access network 109, as well as the collection of performance metrics and / or key performance indicators (typically, network data 102). Additionally, the service and management orchestrator 112 can control aspects of the non-real-time RIC 122 and the near-real-time RIC 124. The non-real-time RIC 122 can provide non-real-time (e.g., greater than one second) control, optimization, and / or data reporting for RAN elements and resources (such as RUs, DUs, and CUs), workflow management, and the application and characteristics of the near-real-time RIC 124. The near-real-time RIC 124 can provide near-real-time (e.g., millisecond) control, optimization, and / or data reporting for RAN elements and resources via fine-grained data collection and actions. Both the non-real-time RIC 122 and the near real-time RIC 124 can be deployed using a microservices-based containerized architecture. In some embodiments, the near real-time RIC 124 can reside at the edge or in a regional cloud.

[0043] The non-real-time RIC 122 can host one or more applications that manage non-real-time events within the non-real-time RIC 122, such as application 123 (e.g., Figure 1 Application 123 can utilize the functionality exposed by the non-real-time RIC framework via the non-real-time RIC 122. Application 123 can be used to collect network data 102 and / or control and manage RAN elements and resources, such as resources in the near real-time RIC 124, RAN nodes, and / or the O-RAN cloud. Application 123 can also utilize network data 102 and user data (i.e., performance metrics and key performance indicators) to provide recommendations for network optimization and operational guidance (e.g., policies) to one or more applications in the near real-time RIC 124. Although shown within the non-real-time RIC 122, any one or more of Application 123 can be performed by a third party separate from the non-real-time RIC 122.

[0044] The near real-time RIC 124 can provide near real-time (e.g., millisecond) control and optimization of RAN elements and resources through fine-grained data collection and actions performed via the E2 interface. For example, the near real-time RIC 124 can be equipped with one or more applications 125 that provide near real-time control of RAN elements and their resources.

[0045] Service and management orchestrator 112, non-real-time RIC 122 and near real-time RIC 124 in Figure 2The system is shown outside of cellular network 120. In other embodiments, one or more of such systems may be logically or physically located within cellular network 120 or another network. Other arrangements of the service and management orchestrator 112, the non-real-time RIC 122, and the near-real-time RIC 124 are also possible. For example, both the non-real-time RIC 122 and the near-real-time RIC 124 may be part of the service and management orchestrator 112, or in another embodiment, the non-real-time RIC 122 and the near-real-time RIC 124 may be implemented separately from the service and management orchestrator 112 (e.g., logically or physically).

[0046] Further details regarding the O-RAN architecture can be found in U.S. Patent Application No. 18 / 620,733, filed March 28, 2024, entitled “Service Management and Orchestration For Private and Public Mobile Networks” (Attorney’s Reference 2014-676US01), which is incorporated herein by reference.

[0047] Figure 2 A block diagram of computing system 240 is also shown, which can be considered as Figure 1 Examples or alternative implementations of the joint operations manager 140 in the context of [the project / system]. Figure 2 The computing system 240 in the middle can be similar to Figure 1 The system operates in a manner similar to the combined operations manager 140 shown. For example, the computing system 240 can jointly manage the cellular network 120 and the local wireless network 130, such as in combination. Figure 1 As described. In Figure 2 The diagram illustrates a computing system 240, describing certain components, modules, and other aspects of the computing system that can implement a system for the joint management of both cellular and Wi-Fi networks, such as a joint operations manager 140. Figure 2 The document also illustrates a computing system 240 to facilitate a description of how such a computing system can operate according to the techniques described herein.

[0048] For ease of explanation, the computing system 240 in Figure 2The computing system 240 is depicted as a single computing system. However, in other embodiments, the computing system 240 may be implemented as multiple devices or computing systems distributed across data centers, multiple data centers, multiple cloud networks, or otherwise. For example, a single computing system may implement the functions described herein as being performed by each of the various modules of the computing system 240, including a collection module 251, a management module 252, a user interface module 253, and a solution module 254. Alternatively or additionally, Figure 2 The modules included in the computing system 240 shown can be implemented through distributed virtualized computing instances (e.g., virtual machines, containers) in data centers, cloud computing systems, server farms and / or server clusters.

[0049] exist Figure 2 In this embodiment, computing system 240 is shown having underlying physical hardware including a power supply 242, one or more processors 244, one or more communication units 245, one or more input devices 246, one or more output devices 247, and one or more storage devices 250. One or more of the devices, modules, storage areas, or other components of computing system 240 may be interconnected to enable inter-component communication (physical, communicative, and / or operational). In some embodiments, such connectivity may be provided via a communication channel, which may include a system bus (e.g., communication channel 243), a network connection, an inter-process communication data structure, or any other method for transmitting data. Although Figure 2 The computing system 240 in the middle can be considered as Figure 1 The example implementation of the Joint Operations Manager 140 is shown, but other implementations are possible.

[0050] In the illustrated embodiment, a power supply 242 of the computing system 240 can provide power to one or more components of the computing system 240. The power supply 242 can receive power from an alternating current (AC) power source in a building, data center, or other location. In some embodiments, the power supply 242 may be or include a battery or device that supplies direct current (DC). The power supply 242 may have intelligent power management or consumption capabilities, and such features may be controlled, accessed, or adjusted by a processor 244 to intelligently consume, distribute, supply, or otherwise manage power. The storage device 250 may include a collection module 251, a management module 252, a user interface module 253, a solution module 254, one or more models 281, and a data storage 259.

[0051] One or more processors 244 of the computing system 240 may implement functions and / or execute instructions associated with the computing system 240 or with one or more modules shown and / or described herein. One or more processors 244 may be, be part of, or include processing circuitry that performs operations according to one or more aspects of this disclosure. Such processors may be mobile processors, desktop processors, server processors, compute nodes, virtualization processors, neural processing units or NPUs, graphics processing units or GPUs, and / or other types of processors or processing circuitry. Processor 244 may execute instructions of one or more processes executing on the computing system 240 and may implement the functions of such processes.

[0052] One or more communication units 245 of the computing system 240 can communicate with devices external to the computing system 240 by sending and / or receiving data, and in some respects can function as both an input device and an output device. The communication units 245 enable the computing system 240 to communicate with other computing devices and systems using any suitable communication protocol (e.g., TCP / IP) and through any suitable medium. In some or all of these cases, one or more communication units 245 can communicate with other devices or computing systems via a network. For example, the communication units 245 enable the computing system 240 to communicate with… Figure 2 Communicates with any other device or system shown, such as cellular network 120, local wireless network 130, and / or devices included on these networks.

[0053] One or more input devices 246 may represent any input device of the computing system 240, and one or more output devices 247 may represent any output device of the computing system 240. Input devices 246 and / or output devices 247 may generate, receive, and / or process output from any type of device capable of outputting information to a person or machine. For example, one or more input devices 246 may generate, receive, and / or process input in the form of electrical, physical, audio, image, and / or visual input (e.g., peripheral devices, keyboards, microphones, cameras). Accordingly, one or more output devices 247 may generate, receive, and / or process output in the form of electrical and / or physical output (e.g., peripheral devices, actuators).

[0054] One or more storage devices 250 within the computing system 240 may store information for processing during operation of the computing system 240. Storage devices 250 may store program instructions and / or data associated with one or more modules described according to one or more aspects of this disclosure. One or more processors 244 and one or more storage devices 250 may provide an operating environment or platform for such modules, which may be implemented as software, but in some embodiments may include any combination of hardware, firmware, and software. One or more processors 244 may execute instructions, and one or more storage devices 250 may store instructions and / or data of one or more modules. The combination of processors 244 and storage devices 250 may retrieve, store, and / or execute instructions and / or data of one or more applications, modules, or software. Processors 244 and / or storage devices 250 may also be operatively coupled to one or more other software and / or hardware components, including but not limited to one or more components of the computing system 240 and / or one or more devices or systems shown or described as connected to the computing system 240.

[0055] The collection module 251 can perform functions related to collecting network data 102 from the cellular network 120 and collecting network data 103 from the local wireless network 130. Typically, the collection module 251 can perform the functions described herein. Figure 1 The Joint Operations Manager 140 performs some of the collection functions.

[0056] Management module 252 can perform functions related to the joint management of cellular network 120 and local wireless network 130, including detecting and handling congestion on cellular network 120 and / or local wireless network 130, and detecting and handling abnormal conditions associated with user equipment 104 attached to cellular network 120 or local wireless network 130. Typically, management module 252 can perform functions related to... Figure 1 The Joint Operations Manager 140 performs some of the functions, including detection and congestion handling, anomaly detection and handling, and others.

[0057] User interface module 253 can perform functions related to generating a user interface that presents information about the joint management of cellular network 120 and local wireless network 130. The user interface can be presented at administrator device 260 for review by administrator 261. As further described herein, such a user interface can highlight or report congestion, anomalies, and other conditions. The user interface can propose or report actions associated with such reported conditions.

[0058] Solution module 254 can perform functions to remedy any situation identified by management module 252. Solution module 254 can output control signals via a network (e.g., network 115) that have the effect of altering the operation of network hardware associated with cellular network 120, local wireless network 130, and / or one or more user equipment 104, thereby remedying the identified situation. In some cases, such actions can be performed automatically by computing system 240, or in others, such actions can be first proposed to an administrator and then performed based on input from the administrator.

[0059] The internal data storage 259 of the computing system 240 can represent any suitable data structure or storage medium for storing network data 102 associated with the cellular network 120, network data 103 associated with the local wireless network 130, information for training or applying model 281, information for generating user interfaces, and / or other information. The information stored in the internal data storage 259 can be searchable and / or categorized, allowing one or more modules within the computing system 240 to provide input requesting information from the internal data storage 259 and, in response to that input, receive information stored in the internal data storage 259. The internal data storage 259 can be primarily maintained by the management module 252.

[0060] Model development system 280 is a system for training and / or developing models (such as artificial intelligence or machine learning models). Model development system 280 may be implemented separately from computing system 240 and may provide off-site or cloud-based services for training model 281. Model development system 280 may access historical or other data to train model 281 used in production by computing system 240. In some embodiments, model development system 280 may receive data from computing system 240 or another source that can be used as the basis for training data.

[0061] The model development system 280 can be implemented by any suitable computing system, which may include one or more server computers, workstations, appliances, cloud computing systems, mainframes, and / or other computing devices. Such a computing system may represent or be implemented through one or more virtualized computing instances (e.g., virtual machines, containers) of a data center, cloud computing system, server farm, and / or server cluster. Furthermore, although shown as being implemented separately from computing system 240, in some embodiments, the model development system 280 may be part of computing system 240 (i.e., logically or physically part of computing system 240).

[0062] In operation, and according to one or more aspects of this disclosure, computing system 240 can collect metrics and events associated with cellular network 120. For example, it can... Figure 2 In the embodiments described in the context of the present invention, the collection module 251 of the computing system 240 causes the communication unit 245 to output one or more signals through the network 115. One or more elements of the cellular network 120 receive the signals and determine that the signals correspond to one or more requests 101 seeking information about performance metrics and / or key performance indicators associated with the cellular network 120.

[0063] For example, the service and management orchestrator 112 can receive one or more requests 101 and respond by sending metrics in the form of network data 102 via network 115. The communication unit 245 of the computing system 240 detects the response signal via network 115 and outputs information about the response signal to the collection module 251. The collection module 251 determines that the response signal corresponds to network data 102 from the service and management orchestrator 112. The collection module 251 stores the network data 102 from the service and management orchestrator 112 in the data storage 259.

[0064] Alternatively or additionally, non-real-time RIC 122 and / or near-real-time RIC 124 may receive request 101 and respond by sending network data 102 (e.g., metrics collected by RIC 122 or 124) via network 115. In such an embodiment, collection module 251 of computing system 240 receives network data 102 and determines that network data 102 corresponds to network data 102 collected by non-real-time RIC 122 and / or near-real-time RIC 124. Collection module 251 stores the network data 102 from non-real-time RIC 122 and / or near-real-time RIC 124 in data storage 259.

[0065] Alternatively or additionally, radio access network 109 and / or mobile core network 105 may receive request 101 and respond by sending network data 102 (e.g., metrics collected within cellular network 120). In such an embodiment, collection module 251 receives network data 102 and determines that network data 102 corresponds to network data 102 collected by radio access network 109 and / or mobile core network 105. Collection module 251 stores the network data 102 collected by radio access network 109 and / or mobile core network 105 in data storage 259.

[0066] Alternatively or additionally, various other elements of the cellular network 120 or an element management system that manages aspects of the cellular network 120 may receive request 101 and respond by sending network data 102. In such an embodiment, collection module 251 receives the sent network data 102 and determines that the network data 102 corresponds to network data 102 collected by other elements of the cellular network 120 or by the element management system of the cellular network 120. Collection module 251 stores the network data 102 collected by the cellular network 120 or the element management system in data storage 259.

[0067] In some embodiments, network data 102 may include telemetry data and / or performance metrics and / or key performance indicators (KPIs) related to cellular network 120. Network data 102 may include, for example, sequential metrics such as aggregated transmission or reception of information flows per radio cell (or base station 106), transmission or reception of data per user equipment 104, information regarding the allocation and utilization of physical resource blocks (PRBs) for radio cells, the number of user equipment 104 attached to a cell, the total number of active user equipment 104, alarms generated by radio access network 109 and / or mobile core network 105, logs or other, and / or other information and metrics associated with events within cellular network 120. Computing system 240 may also monitor and / or collect network data 102 to generate combined or aggregated performance metrics and / or KPIs associated with cellular network 120.

[0068] Despite Figure 2 In this embodiment, network data 102 is described as being sent to computing system 240 in response to a request 101 initiated by computing system 240. However, in other embodiments, network data 102 may be sent to computing system 240 without first receiving a specific request 101. For example, the service and management orchestrator 112, the non-real-time RIC 122, and / or the near real-time RIC 124 may occasionally, periodically, or continuously send at least some network data 102 to computing system 240 without first receiving a request 101 for such data. Similarly, components or component management systems of radio access network 109, mobile core network 105, and / or cellular network 120 may occasionally, periodically, or continuously send at least some network data 102 to computing system 240 without first receiving a request 101 for such data.

[0069] The computing system 240 can also collect metrics and events associated with the local wireless network 130. For example, continuing in Figure 2In the embodiment described in the context of the prior art, the collection module 251 of the computing system 240 causes the communication unit 245 to output another set of one or more signals through the network 115. One or more elements of the local wireless network 130 receive the signals and determine that the signals correspond to request 101, thereby seeking information about performance metrics and / or key performance indicators associated with the local wireless network 130.

[0070] For example, one or more access points 131 may receive request 101 and respond by sending metrics (e.g., performance metrics or indicators collected by access points 131) in the form of network data 103 via network 115. The communication unit 245 of the computing system 240 detects the response signal via network 115 and outputs information about the response signal to the collection module 251. The collection module 251 determines that the response signal corresponds to network data 103 from one or more access points 131. The collection module 251 stores the network data 103 from these access points 131 in data storage 259.

[0071] Furthermore, in the case where the local wireless network 130 includes a Wi-Fi manager 132, the Wi-Fi manager 132 can also receive one or more requests 101 and respond by sending network data 103 via network 115. In such an embodiment, the collection module 251 receives the network data 103 and determines that the network data 103 corresponds to network data 103 collected, obtained, or otherwise generated by the Wi-Fi manager 132 or other elements of the local wireless network 130 (e.g., one or more network resources 136 or network hardware within the local wireless network 130).

[0072] In some embodiments, network data 103 may include telemetry data and / or performance metrics and / or key performance indicators (KPIs) related to the local wireless network 130. Network data 103 may include, for example, sequential metrics such as aggregated transmission or reception of information flows per access point 131, aggregated transmission or reception of information flows per site or physical location across multiple access points 131, transmission or reception of data per user equipment 104, information about the number of user equipment 104 attached to each access point 131, logs, and / or other information and metrics. The computing system 240 may also monitor and / or collect network data 103 to generate combined or aggregated performance metrics and / or KPIs associated with the local wireless network 130.

[0073] Moreover, despite Figure 2In this embodiment, network data 103 is described as an element sent to computing system 240 and to local wireless network 130 in response to a request 101 initiated by computing system 240. However, in other embodiments, network data 103 may be sent to computing system 240 without first receiving a specific request 101. For example, one or more access points 131 may occasionally, periodically, or continuously send at least some network data 103 to computing system 240 without first receiving a request 101 for such data. Similarly, other elements of local wireless network 130 (including Wi-Fi manager 132 or network resource 136) may occasionally, periodically, or continuously send at least some network data 103 to computing system 240 without first receiving a request 101 for such data.

[0074] The computing system 240 can train one or more models 281 using information collected from the cellular network 120 and / or the local wireless network 130. For example, refer again... Figure 2 In the embodiment described in the context of the above, the management module 252 of the computing system 240 causes the communication unit 245 to output a series of signals through the network 115. The model development system 280 detects these signals and determines that they correspond to instructions and / or data for training various machine learning models (e.g., model 281). The model development system 280 also determines that these signals include data (or instructions for obtaining data) that can be used as training data for training model 281 to make predictions about the joint operation of cellular network 120 and local wireless network 130. Therefore, such training data can be derived from both network data 102 (i.e., including metrics about cellular network 120) and network data 103 (i.e., including metrics about local wireless network 130).

[0075] The model development system 280 can train various models 281. For example, still refer to Figure 2 The model development system 280 applies appropriate machine learning and / or artificial intelligence techniques to the training data. Such techniques may include performing supervised or unsupervised learning to develop a model capable of making inferences based on a joint dataset corresponding to network data 102 and network data 103. In some embodiments, as described herein, the model development system 280 may use data from... Figure 2 The model 281 is trained using data derived from the operation of the cellular network 120 and local wireless network 130 depicted herein. However, the model development system 280 may alternatively or additionally rely on other suitable training data, which may be derived from other networks (e.g., cellular networks, Wi-Fi networks) or any other network, particularly those involving similar networks. Figure 2The overlapping overlays of the overlapping networks shown are derived from these networks.

[0076] Model development system 280 can prepare model 281 for jointly managing the operation of cellular network 120 and local wireless network 130. For example, once model 281 is trained, model development system 280 outputs a series of signals through network 115. Communication unit 245 of computing system 240 detects these signals and outputs information about these signals to management module 252. Management module 252 determines that these signals correspond to a set of trained models 281 capable of generating inferences based on a joint set of network data 102 and network data 103. Management module 252 stores model 281 in storage device 250 and configures model 281 to generate inferences when prompted with production data describing the operation of cellular network 120 and local wireless network 130 (e.g., current network data 102 and network data 103).

[0077] As described below, model 281 can be trained to generate inferences about joint operations and events occurring in cellular network 120 and / or local wireless network 130. Such models can typically cover network congestion, abnormal data usage, abnormal device attachment, energy-saving opportunities, network misconfiguration, potential security threats, and network hardware maintenance.

[0078] For example, model development system 280 can train one or more models 281 to make inferences about congestion in cellular network 120 and / or local wireless network 130. To this end, model development system 280 can apply data-driven machine learning algorithms to analyze traffic patterns and quality of service metrics to identify existing congestion or predict congestion before it occurs on cellular network 120 or local wireless network 130.

[0079] The model development system 280 can also train one or more models 281 to detect data usage anomalies or anomalies regarding traffic patterns associated with user equipment 104. For example, one or more models 281 can assess the current data usage patterns associated with user equipment 104 and determine if such usage patterns are inconsistent with historical usage patterns. Such determination can be based on the total data throughput typically associated with a given user equipment 104 (or a set of user equipment 104) that can be attached to cellular network 120 or local wireless network 130. Specifically, one or more models 281 can correlate the number and / or type of user equipment 104 attached to the network with the total data throughput and identify whether traffic patterns are inconsistent with normal operation. In cases where traffic patterns appear anomalous, model 281 can predict that some of the user equipment 104 are not functioning correctly (e.g., some of the user equipment 104 may be able to attach to cellular network 120 or local wireless network 130 but cannot access one or more internal / external applications).

[0080] The model development system 280 can also train one or more models 281 to detect anomalies related to which network a given user equipment 104 is attached to. For example, one or more models 281 can assess the time and date when a given user equipment 104 attaches to cellular network 120 or local wireless network 130. For example, models 281 can be trained to understand that some user equipment 104 tends to attach to one of the networks (i.e., cellular network 120 or local wireless network 130) at certain times of day or week. If the network attachment pattern of a given user equipment 104 is inconsistent with the normal pattern, such a model 281 can infer that the user equipment 104 is unable to access the network due to a problem. Model 281 can perform this monitoring at the access point 131 level of local wireless network 130, or at the cell level and / or radio resource control (RRC) level, for problems related to radio access network 109, or at the non-access stratum (NAS) level, for problems related to mobile core network 105.

[0081] The model development system 280 can also train one or more models 281 to identify energy-saving opportunities. For example, model 281 can identify off-peak usage times during which energy savings can be achieved by turning off one or more Wi-Fi access points 131, causing some user devices 104 to rely on cellular radios with wider coverage. In other words, model 281 can identify opportunities to disable Wi-Fi access points 131 that overlap with the cellular coverage area provided by cellular network 120 based on observed traffic associated with user devices 104 and the time of day. When model 281 determines that observed traffic associated with user devices 104 has risen to normal levels, the model can enable Wi-Fi access points 131, and vice versa.

[0082] The model development system 280 can train one or more models 281 to identify network misconfigurations. For example, one or more models 281 can be trained to identify incorrect Maximum Transmission Unit (MTU) values ​​for the User Plane Function (UPF). Model 281 can identify such misconfigurations by monitoring KPIs on the N3 interface (the data plane connection between the RAN and the UPF) and the N6 interface (the connection point between the UPF of the 5G network and the wider Internet), and determine when packet count spikes occur upstream of N6 compared to N3.

[0083] The model development system 280 can train one or more models 281 to identify anomalies that suggest a security threat. For example, one or more models 281 can detect unusual behavior indicating a security threat, such as an attempted distributed denial-of-service (DDoS) attack or an unauthorized network access attempt. Such models 281 can be trained to learn normal traffic patterns and identify any significant deviations from these patterns. Once identified by such models, actions can be taken (e.g., by the solution module 254 of the computing system 240), which may include automated blocking measures or notifying the security team to mitigate the risk.

[0084] The model development system 280 can also train one or more models to predict implementations that may require maintenance of network hardware. For example, one or more models 281 can be trained to monitor the operational health of network hardware, such as radios and access points, thereby predicting hardware failures. Through data analysis of temperature, memory usage, and historical maintenance logs, such a model 281 can identify potential failures based on historical data and alarms. Once identified by such a model, preventative maintenance actions can be initiated for various network hardware (e.g., cellular radios and access points 131) (e.g., by solution module 254 of computing system 240).

[0085] The computing system 240 can apply one or more models 281 to manage the operation of the cellular network 120 and the local wireless network 130. For example, refer again... Figure 2 In the embodiment described in the context of the present invention, collection module 251 monitors current operations occurring in cellular network 120 and local wireless network 130. When user equipment 104 is connected to either cellular network 120 or local wireless network 130, collection module 251 collects network data 102 from cellular network 120 and network data 103 from local wireless network 130. Collection module 251 collects such data by automatically receiving data or in response to request 101, as described above. Collection module 251 outputs information about the collected network data to management module 252. To correlate per-device metrics from different networks, management module 252 correlates and / or maps device identifiers under all monitored networks (i.e., in this embodiment, cellular network 120 and local wireless network 130). One implementation of device identifier mapping may include SIM-based EAP-AKA authentication of Wi-Fi users via user data management (UDM) module of computing system 240 (e.g., included within functions performed by management module 252). The same UDM can also manage authentication for private cellular networks, thus mapping network-specific device identifiers to management module 252. Management module 252 is applied to the collected and mapped data by one or more models 281 trained to predict or identify various network conditions. Management module 252 receives one or more predictions from model 281 regarding the condition of cellular network 120 and local wireless network 130 (or regarding user equipment 104 attached to such networks). In some embodiments, management module 252 outputs information about the predictions to user interface module 253, enabling the generation of one or more user interfaces to be presented to the user. Management module 252 also outputs information about the predictions to solution module 254. Solution module 254 determines mitigation strategies based on the predictions made by model 281 and, where appropriate, executes or proposes actions to resolve any problems predicted by model 281.

[0086] In one embodiment, computing system 240 can identify conditions related to congestion occurring or anticipated in cellular network 120 and / or local wireless network 130. For example, management module 252 selects and applies one or more models 281 trained to predict congestion based on collected and mapped data derived from current network data 102 and 103. Management module 252 receives information from model 281 identifying actual or anticipated congestion. Management module 252 outputs information about actual or anticipated congestion to solution module 254. Solution module 254 determines strategies for preventing and / or mitigating congestion, which may include directing traffic to optimal paths, dynamic resource allocation, and switching some user equipment 104 from cellular network 120 to local wireless network 130 (or, depending on the situation, switching from local wireless network 130 to cellular network 120). In some embodiments where congestion occurs or is anticipated, management module 252 and / or solution module 254 monitor network data 102 and 103 and preemptively block certain users attached to cellular network 120 or local wireless network 130 at specific times to prevent congestion or overload.

[0087] If solution module 254 determines a mitigation strategy involving moving some user equipment 104 from one network to another, solution module 254 may select user equipment 104 to move on a random basis or based on the usage pattern of each user equipment 104 (e.g., selecting user equipment with higher usage). However, the selection of which user equipment 104 to move may also be performed based on a classification associated with each user equipment 104. For example, management module 252 of computing system 240 may classify each user equipment 104 as primarily configured for cellular access (e.g., cellular network 120) or primarily configured for Wi-Fi access (e.g., local wireless network 130). User equipment 104 with such classification may, in most cases, be attached to the primary network they identify, and may only be allowed to attach to a non-primary network if congestion or other problems are predicted on the primary network. Other categories of user equipment 104 that may affect remedial work may include Wi-Fi only (e.g., for devices with Wi-Fi capability but no cellular capability), 4G cellular only (e.g., for devices that are only compatible with 4G cellular networks but no Wi-Fi capability), 5G cellular only (e.g., for devices that are only compatible with 5G cellular networks but no Wi-Fi capability), any cellular (e.g., for devices with both 4G and 5G capabilities but no Wi-Fi capability), or both Wi-Fi and cellular (Bonding / MPTCP).

[0088] In some embodiments, solution module 254 may automatically perform actions based on a remediation strategy. In other embodiments, solution module 254 may enable user interface module 253 to report congestion and / or proposed mitigation strategies (i.e., for review by administrator 261) through a user interface presented at administrator device 260, and to perform actions based on the remediation strategy after receiving authorization from administrator 261.

[0089] In another embodiment, computing system 240 can detect anomalies based on a comparison of network data 102 and 103 derived from the current operation of networks 120 and 130 with historical network data from those networks. For example, still referring to Figure 2 The management module 252 selects and applies one or more models 281 trained to identify anomalies (e.g., changes in data usage associated with user equipment 104, unusual network attachment patterns of user equipment 104, unusual behavior associated with joint activities across networks 120 or 130, or activities suggesting a security threat). The management module 252 receives information about predicted anomalies from the models 281 based on comparisons of current and historical data. The management module 252 outputs the prediction information to the solution module 254. The solution module 254 determines strategies for mitigating, resolving, or remediating any predicted anomalies. Such mitigation strategies may include proposing or implementing changes or fixes to one or more user equipment 104, or taking security precautions (e.g., applying automated blocking measures or notifying the security team to mitigate risk).

[0090] Figure 2 The modules shown (e.g., collection module 251, management module 252, user interface module 253, and solution module 254) and / or modules shown or described elsewhere in this disclosure can perform operations described using software, hardware, firmware, or a mixture of hardware, software, and firmware residing in and / or executing on one or more computing devices. For example, a computing device may utilize multiple processors or multiple devices to execute one or more such modules. A computing device may execute one or more such modules as a virtual machine executing on the underlying hardware. One or more such modules may execute as one or more services in an operating system or computing platform. One or more such modules may execute as one or more executable programs at the application layer of a computing platform. In other embodiments, the functionality provided by the modules may be implemented by dedicated hardware devices.

[0091] While certain modules, data stores, components, programs, executables, data items, functional units, and / or other items included within one or more storage devices may be shown individually, one or more such items may be combined and operated as a single module, component, program, executable, data item, or functional unit. For example, one or more modules or data stores may be combined or partially combined such that they operate or provide functionality as a single module. Furthermore, one or more modules may interact with each other and / or operate in combination with each other, such that, for example, one module serves as a service or extension of another module. Moreover, each module, data store, component, program, executable, data item, functional unit, or other item shown within the storage device may include multiple components, subcomponents, modules, submodules, data stores, and / or other components or modules or data stores not shown.

[0092] Furthermore, each module, data store, component, program, executable file, data item, functional unit, or other item shown within the storage device can be implemented in various ways. For example, each module, data store, component, program, executable file, data item, functional unit, or other item shown within the storage device can be implemented as a downloadable or pre-installable application or "app". In other embodiments, each module, data store, component, program, executable file, data item, functional unit, or other item shown within the storage device can be implemented as part of an operating system that executes on a computing device.

[0093] Figure 3A , Figure 3B , Figure 3C , Figure 3D and Figure 3E This is a conceptual diagram illustrating an example user interface presented by a user interface device according to one or more aspects of this disclosure. Figures 3A to 3E Each of the user interfaces 300 presented in the middle (i.e., user interface 300A, user interface 300B, user interface 300C, user interface 300D, and user interface 300E, respectively) can correspond to the interface provided by the user interface 300. Figure 1 The joint operations manager 140 in the middle presents or outputs the user interface 300. Each of the user interfaces 300 can also be... Figure 2 The computing system 240 in the middle is presented or output, and in such an embodiment, any of the user interfaces 300 can be presented by an output device, such as as Figure 2 The display device is included as part of the computing system 240. This display device can be considered as... Figure 2 An embodiment of the output device 247 shown. In some embodiments, such as when the display device is a sensitive display (e.g., a "touchscreen"), the display device can also be used as... Figure 2An embodiment of the input device 246 shown. Figures 3A to 3E One or more aspects of the user interface shown in the document can be found in this document. Figure 2 The description is made in the context of the computing system 240.

[0094] Figure 3A This is for use with multiple wireless networks (such as in...) Figure 1 Network system 100 or Figure 2 The system provides a unified, visual example user interface for various use cases associated with the network system 200. Specifically, the user interface 300A provides information on six use cases, each presented as a display element radiating from the central "Action" display element in the user interface 300A. The six use cases corresponding to the display elements include (in counter-clockwise order from left to right): (1) Traffic steering (or congestion), indicating 3 AI-Ops actions ("AI-Ops actions"), (2) Energy saving, indicating 8 actions, (3) Network misconfiguration, indicating 4 actions, (4) Data usage anomaly detection, indicating 10 actions, (5) Predictive maintenance, indicating 3 actions, and (6) User equipment attachment anomaly detection, indicating 5 actions.

[0095] The computing system 240 can present a user interface 300A in response to input from an administrator (e.g., administrator 261 operating administrator device 260, which may be integrated into the computing system 240). For example, in a scenario where... Figure 2 and Figure 3A In the embodiment described in the context of the present invention, the input device 246 of the computing system 240 detects input and outputs information about the input to the user interface module 253 of the computing system 240. The user interface module 253 determines that the input corresponds to a request to present unified network operation information within the network system 200. The user interface module 253 collects information about the cellular network 120 and the local wireless network 130 by accessing such information in data storage 259 within the storage device 250 of the computing system 240. The user interface module 253 generates data sufficient to render the user interface on a display device, which may be one of the output devices 247 included within the computing system 240. The user interface module 253 uses this data to cause the display device to present the user interface 300A, such as... Figure 3A As shown. In some embodiments, such as when the administrator device 260 is not integrated into the computing system 240, the computing system 240 may output a signal via network 115 that enables the user interface to be presented remotely (e.g., at a remote administrator device 260).

[0096] exist Figure 3AIn this context, a display device (e.g., one of the output devices 247) presents a user interface 300A, which includes... Figure 3A The visualization depicted in the image. Once as... Figure 3A As shown, the user interface 300A can respond (e.g., via cursor 301) to the selection of a traffic-directed / congestion use case by presenting information about three “AI-Ops Actions” in a panel displayed at the bottom of the user interface 300A. This panel identifies each of the three AI-Ops Actions by ID, description, initiation time, cleanup time, status, and action (proposed or automated).

[0097] The computing system 240 can present additional information about one or more of the shown "AI-Ops actions." For example, refer to... Figure 2 And now Figure 3B The user interface module 253 receives an indication of input associated with the selection of a first AI-Ops action near the bottom of 300B via cursor 301. In response, the user interface module 253 generates user interface information associated with that specific AI-Ops action and causes the output device 247 to... Figure 3B This information is displayed in the "Traffic Direction Details" panel on the right side of the 300B user interface.

[0098] In a similar manner, computing system 240 can present information about different use cases. For example, refer to Figure 2 and Figure 3C The user interface module 253 receives an indication of the input associated with the selection of the "Network Error Configuration Detection" use case via cursor 301. In response, the user interface module 253 updates the user interface 300C. Figure 3C (in Chinese) to present information about four AI-Ops associated with this use case, such as Figure 3C The table shown is located in the bottom panel of the user interface 300C. Note that the "AI-Ops Actions" table at the bottom of the user interface 300C presents information about four network error configuration actions. When the user interface module 253 receives an instruction corresponding to (e.g., via cursor 301) selecting any item in this table, the user interface module 253 causes 300C to update to user interface 300D, as shown. Figure 3D As shown. In Figure 3D In the middle, the "Network Misconfiguration Detection Details" panel is displayed along the right side of the user interface 300D.

[0099] Figure 3EThe presentation of user interface 300E is shown, which provides information about the number of events associated with each of the six use cases in a stacked time-based graph (see the sequence diagram along the top of user interface 300E). The four events depicted in the sequence diagram along the top of user interface 300E are listed below the graph, where each event is located within its own panel in user interface 300E.

[0100] Figure 4A and Figure 4B This is a conceptual diagram illustrating another example user interface presented by a user interface device according to one or more aspects of this disclosure. Figure 4A and Figure 4B Each of the user interfaces 400 presented in the middle (i.e., user interfaces 400A and 400B respectively) can correspond to the interface provided by the user interface 400. Figure 1 Joint Operations Manager 140 or Figure 2 The user interface 300 shown is the user interface 300 presented or output. Similar to user interface 300, any of the user interfaces 400 can be an output device of the joint operations manager 140 or a computing system 240 (e.g., included as...). Figure 2 The display device 247 is a part of the computing system 240 in the computer system 240 to present the data.

[0101] Figure 4A A three-dimensional campus view of network devices is presented, which can be any network device included in the radio access network 109 or mobile core network 105 of cellular network 120, or any access point 131 of local wireless network 130. The panel located to the right of user interface 400A lists the devices depicted within user interface 400A and provides the names, IP addresses, and statuses of such devices.

[0102] Figure 4B yes Figure 4A An alternative view of a layer depicted in the user interface 400A. Figure 4B The user interface 400B in the computing system 240 can be responded to (e.g., by cursor 401) by the user interface module 253 in response to the detection of an object. Figure 4A The user interface 400A is presented in the form of a selection of the first layer of the 3D campus view presented in the user interface 400A. In the user interface 400B, the panel located on the right side of the user interface 400B lists the devices found on the first layer and provides the name, IP address, and status of such devices.

[0103] Figure 5 This is a flowchart illustrating the operations performed by an example joint operations manager according to one or more aspects of this disclosure. Below is... Figure 1Description in the context of network system 100 Figure 5 In other embodiments, in Figure 5 The operations described herein can be performed by one or more other components, modules, systems, or devices. Additionally, in other embodiments, [the text abruptly ends here]. Figure 5 The operations described may be combined, performed in a different order, omitted, or may include additional operations not specifically illustrated or described.

[0104] exist Figure 5 In the process shown, and according to one or more aspects of this disclosure, the joint operations manager 140 may collect network data (501) associated with the first wireless network. For example, refer to Figure 1 The Joint Operations Manager 140 outputs multiple requests 101 to the Cellular Network 120 via network 115. Components within the Cellular Network 120 detect a series of signals and determine that these signals include requests 101 seeking information about performance metrics, key performance indicators, and / or other information about the Cellular Network 120. Devices and components associated with the Cellular Network 120 respond to requests 101 by outputting network data 102, which is received by the Joint Operations Manager 140 via network 115. Through this process, the Joint Operations Manager 140 can obtain information from the RAN Intelligent Controller (RIC) associated with the Cellular Network 120 (e.g., reference...). Figure 2 Measurements can be obtained directly from cellular network 120, from a component management system that manages switches within cellular network 120, or from other components of cellular network 120. In some embodiments, joint operations manager 140 may receive network data 102 (e.g., measurements and / or other information about cellular network 120) without making a specific request for that information.

[0105] The Joint Operations Manager 140 can collect network data associated with the second wireless network (502). For example, refer again... Figure 1The Joint Operations Manager 140 outputs multiple requests 101 to the local wireless network 130 via network 115. Components within the local wireless network 130 detect a series of signals and determine that these signals include requests 101 seeking information about the local wireless network 130 (e.g., performance metrics, key performance indicators, and / or other information). Devices and components associated with the local wireless network 130 (e.g., access point 131, network resource 136, Wi-Fi manager 132, or other components within the local wireless network 130) respond to requests 101 by outputting network data 103 to the Joint Operations Manager 140 via network 115. Similar to cellular network 120, in some embodiments, the Joint Operations Manager 140 may receive network data (e.g., metrics and / or other information about the local wireless network 130) without making specific requests for that information.

[0106] The Joint Operations Manager 140 can identify user equipment (503) attached to the first wireless network. For example, refer to Figure 1 The Joint Operations Manager 140 evaluates network data 102 and network data 103 received from the cellular network 120 and the local wireless network 130. The Joint Operations Manager 140 identifies one or more user equipments 104 that are attached to the cellular network 120 but not to the local wireless network 130, yet have the capability to be attached to the local wireless network 130. The Joint Operations Manager 140 determines whether the one or more user equipments 104 are located within the wireless coverage area served by both the cellular network 120 and the local wireless network 130.

[0107] The Joint Operations Manager 140 can identify or predict network conditions affecting user equipment (504). For example, in Figure 1 In this process, the Joint Operations Manager 140 also evaluates network data 102 and 103 and determines that there is no network condition affecting user equipment 104 attached to cellular network 120 (the no path from 504). However, in at least some embodiments, the Joint Operations Manager 140 determines, based on network data 102 and 103, that congestion is affecting user equipment 104 attached to cellular network 120 (the yes path from 504).

[0108] The Joint Operations Manager 140 can take actions to remedy network conditions affecting user equipment based on predicted network conditions (505). For example, refer again... Figure 1The Joint Operations Manager 140 evaluates options for remedying congestion within the cellular network 120, which may include potential traffic redirection operations between the cellular network 120 and the local wireless network 130. The Joint Operations Manager 140 determines that the local wireless network 130 is not congested. The Joint Operations Manager 140 selects to move one or more user equipment 104 attached to the cellular network 120 to the local wireless network 130 to alleviate congestion at the cellular network 120. The Joint Operations Manager 140 selects user equipment 104 for movement based on whether such equipment can be attached to the local wireless network 130. The Joint Operations Manager 140 may also additionally select user equipment 104 for movement based on data usage or other characteristics of such user equipment 104.

[0109] The Joint Operations Manager 140 takes action to move User Equipment 104 from Cellular Network 120 to Local Wireless Network 130. To do this, the Joint Operations Manager 140 may send control signals to Cellular Network 120 or its components, instructing each of these components to modify its operation to disconnect a specific User Equipment 104 from Cellular Network 120. The Joint Operations Manager 140 may also send control signals to Local Wireless Network 130 or its components, instructing each component to modify its operation to enable these User Equipment 104 to attach to Local Wireless Network 130. Therefore, the Joint Operations Manager 140 sends control signals to, for example, hardware components within Cellular Network 120 and / or Local Wireless Network 130, instructing them to be effectively controlled to achieve the desired remedy. Thus, the Joint Operations Manager 140 controls the operation of systems, components, or hardware within Cellular Network 120 and / or Local Wireless Network 130 based on predictions made by a model employed by the Joint Operations Manager 140.

[0110] For the processes, apparatus, and other embodiments or illustrations described herein, including any flowcharts or diagrams, certain operations, actions, steps, or events included in any techniques described herein may be performed in a different order, may be added, combined, or omitted entirely (e.g., not all described actions or events are necessary for the practice of these techniques). Furthermore, in some embodiments, operations, actions, steps, or events may be performed concurrently rather than sequentially, for example, through multithreaded processing, interrupt handling, or multiple processors. Other operations, actions, steps, or events may be performed automatically, even if not specifically identified as being performed automatically. Moreover, certain operations, actions, steps, or events described as automatically performed may alternatively not be automatically performed; instead, in some embodiments, such operations, actions, steps, or events may be performed in response to input or another event.

[0111] In the foregoing description, the phrase "some embodiments" has been mentioned occasionally. In this disclosure, references to "some embodiments" are intended to refer to a subset of all feasible embodiments supported by this disclosure. Furthermore, different references to "some embodiments" do not always refer to the same subset of embodiments.

[0112] Some embodiments may be used in conjunction with the following devices and / or networks: devices and / or networks operating according to existing Wireless Gigabit Alliance (WGA) specifications (Wireless Gigabit Alliance Corporation, WiGig MAC and PHY Specification Version 1.1, April 2011, Final Specification) and / or future versions and / or derivatives thereof; devices and / or networks operating according to existing IEEE 802.11 standards (IEEE 802.11-2012, IEEE Standards for Information Technology – Telecommunications and Information Exchange between Systems LANs and Metropolitan Area Networks – Specific Requirements Part 11: Wireless LAN Media Access Control (MAC) and Physical (PHY) Specifications, March 29, 2012; IEEE 802.11ac-2013 (“IEEE P802.11ac-2013, IEEE Standards for Information Technology – Telecommunications and Information Exchange between Systems – LANs and Metropolitan Area Networks – Specific Requirements – Part 11: Wireless LAN Media Access Control (MAC) Layer and Physical (PHY) Layer Specifications – Amendment 4: For use in 6 "Enhanced Ultra-High Throughput for Sub-GHz Bands", December 2013; IEEE 802.11ad ("IEEE P802.11ad-2012, IEEE Standards for Information Technology - Telecommunications and Information Exchange Between Systems - Local Area Networks and Metropolitan Area Networks - Specific Requirements - Part 11: Specifications for Wireless LAN Media Access Control (MAC) and Physical (PHY) Layers - Amendment 3: Enhanced Ultra-High Throughput for 60 GHz Band", December 28, 2012); IEEE 802.11REVmc ("IEEE..." IEEE 802.11-REVmcTM / D3.0, Draft Standard for Information Technology, June 2014 – Telecommunications and Information Exchange Between Systems – Local Area Networks and Metropolitan Area Networks – Specific Requirements – Part 11: Wireless LAN Media Access Control (MAC) and Physical Layer (PHY) Specifications; IEEE 802.11-ay (P802.11ay Standard for Information Technology – Telecommunications and Information Exchange Between Systems – Specific Requirements – Part 11: Wireless LAN Media Access Control (MAC) and Physical Layer (PHY) Specifications – Amendment: Enhanced Throughput for Operation in Unlicensed Bands Above 45 GHz); IEEE 802.11-2016 and / or future versions and / or derivatives of these standards, and devices and / or networks, in accordance with existing Wi-Fi Alliance (WFA) Peer-to-Peer (P2P) specifications (Wi-Fi). Devices and / or networks operating under the P2P technical specification (version 1.5, August 2014) and / or future versions and / or derivatives thereof, devices and / or networks operating under existing cellular specifications and / or protocols (e.g., 3GPP, 3GPP Long Term Evolution (LTE)) and / or future versions and / or derivatives thereof, units and / or devices operating as part of the above networks or using any one or more of the above protocols, etc.

[0113] Some embodiments may be used in conjunction with one-way and / or two-way radio communication systems, cellular radio-telephone communication systems, mobile phones, cell phones, wireless phones, personal communication system (PCS) devices, PDA devices incorporating wireless communication devices, mobile or portable global positioning system (GPS) devices, devices incorporating GPS receivers or transceivers or chips, devices incorporating RFID elements or chips, multiple-input multiple-output (MIMO) transceivers or devices, single-input multiple-output (SIMO) transceivers or devices, multiple-input single-output (MISO) transceivers or devices, devices having one or more internal antennas and / or external antennas, digital video broadcasting (DVB) devices or systems, multi-standard wireless devices or systems, wired or wireless handheld devices (e.g., smartphones), Wireless Application Protocol (WAP) devices, etc.

[0114] Some embodiments may be used in combination with one or more types of wireless communication signals and / or systems, such as radio frequency (RF), infrared (IR), frequency division multiplexing (FDM), orthogonal FDM (OFDM), orthogonal frequency division multiple access (OFDMA), time division multiplexing (TDM) of FDM, time division multiple access (TDMA), multi-user MIMO (MU-MIMO), space division multiple access (SDMA), extended TDMA (E-TDMA), General Packet Radio Service (GPRS), extended GPRS, code division multiple access (CDMA), wideband CDMA (WCDMA), and CDMA. 2000, Single-carrier CDMA, Multi-carrier CDMA, Multi-carrier Modulation (MDM), Discrete Multi-carrier (DMT), Bluetooth, Global Positioning System (GPS), Wi-Fi, Wi-Max, ZigBee™, Ultra-Wideband (UWB), Global System for Mobile Communications (GSM), 2G, 2.5G, 3G, 3.5G, 4G, 5G or 6G mobile networks, 3GPP, Long Term Evolution (LTE), LTE Advanced, Enhanced Data Rate GSM Evolution (EDGE), etc. Other embodiments may be used in various other devices, systems, and / or networks.

[0115] Some illustrative embodiments can be used in conjunction with a WLAN (Wireless Local Area Network) (e.g., a Wi-Fi network). Other embodiments can be used in conjunction with any other suitable wireless communication network, such as a wireless local area network, a "piconet", a WPAN, a WVAN, etc.

[0116] Some embodiments may be used in conjunction with wireless communication networks communicating on the 2.4 GHz, 5 GHz, and / or 60 GHz frequency bands. However, other embodiments may be implemented using any other suitable wireless communication frequency band, such as extremely high frequency (EHF) bands (millimeter wave (mmWave) bands) (e.g., bands between 20 GHz and 300 GHz, WLAN bands, WPAN bands, bands according to WGA specifications, etc.).

[0117] While only a few simple embodiments of various device configurations have been provided above, it should be understood that many variations and substitutions are possible. Furthermore, this technique is not limited to any particular channel but can generally be applied to any frequency range / channel. Additionally, and as discussed, this technique can be useful in unlicensed spectrum.

[0118] All publications, patents, and patent applications mentioned herein are incorporated herein by reference. This disclosure is intended to control the extent to which any material incorporated herein by reference conflicts with this disclosure.

[0119] For ease of illustration, only a limited number of devices (e.g., user equipment 104, access point 131, base station 106, non-real-time RIC 122, near real-time RIC 124, service and management orchestrator 112, joint operations manager 140, computing system 240, and others) are shown in the description herein. However, techniques according to one or more aspects of this disclosure can be implemented using many more such systems, components, devices, modules, and / or other items, and collective references to such systems, components, devices, modules, and / or other items can refer to any number of such systems, components, devices, modules, and / or other items.

[0120] The description contained herein depicts at least one example implementation of aspects of this disclosure. However, the scope of this disclosure is not limited to such implementations. Therefore, other embodiments or alternative implementations of the systems, methods, or techniques described herein (in addition to those shown) may be appropriate in other cases. Such implementations may include a subset of the devices and / or components included in the illustrations and / or may include additional devices and / or components not specifically shown.

[0121] The detailed descriptions above are intended as descriptions of various configurations and are not intended to represent the only configuration in which the concepts described herein can be practiced. Specific details are included in the detailed implementations to provide a full understanding of the various concepts. However, these concepts can be practiced without these specific details. In some instances, well-known structures and components are shown in block diagrams in the referenced illustrations to avoid obscuring these concepts.

[0122] Therefore, while specific illustrations may be used to describe one or more implementations of various systems, devices, and / or components, these systems, devices, and / or components may be implemented in several different ways. For example, one or more devices shown herein as independent devices may alternatively be implemented as a single device; one or more components shown herein as independent components may alternatively be implemented as a single component. Moreover, in some embodiments, one or more devices shown herein as a single device may alternatively be implemented as multiple devices; one or more components shown herein as a single component may alternatively be implemented as multiple components. Each of such multiple devices and / or components may be directly coupled via wired or wireless communication and / or remotely coupled via one or more networks. Furthermore, one or more devices or components shown herein may alternatively be implemented as part of another device or component not shown in these illustrations. In this and other ways, some of the functions described herein may be performed by more than two devices or components via distributed processing.

[0123] Additionally, certain operations, techniques, features, and / or functions may be described herein as being performed by a specific component, device, and / or module. In other embodiments, these operations, techniques, features, and / or functions may be performed by different components, devices, or modules. Therefore, some operations, techniques, features, and / or functions that may be attributed to one or more components, devices, or modules in other embodiments may be attributed to other components, devices, and / or modules, even if not specifically described in this manner herein. References herein to “real-time” or equivalent phrases are intended to cover near real-time or seemingly near real-time, for example, from the perspective of a reasonable human observer.

[0124] While specific advantages have been identified in conjunction with the description of some embodiments, various other embodiments may include some, all, or none of the listed advantages. Other advantages (technical or otherwise) may become apparent to those skilled in the art based on this disclosure. Furthermore, although specific embodiments have been disclosed herein, any number of techniques (whether currently known or not) may be used to implement aspects of this disclosure, and therefore, this disclosure is not limited to the embodiments specifically described and / or shown herein.

[0125] In one or more embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination of hardware, software, and firmware. If implemented in software, the functionality may be stored as one or more instructions or code on and / or transmitted via a computer-readable medium and executed by a hardware-based processing unit. A computer-readable medium may include a computer-readable storage medium, which corresponds to a tangible medium such as a data storage medium, or a communication medium containing any medium that facilitates the transfer of a computer program from one place to another (e.g., according to a communication protocol). In this way, a computer-readable medium may generally correspond to (1) a non-transitory tangible computer-readable storage medium or (2) a communication medium such as a signal or carrier wave. A data storage medium may be any available medium accessible by one or more computers or one or more processors to retrieve instructions, code, and / or data structures for implementing the techniques described in this disclosure. A computer program product may include a computer-readable medium.

[0126] By way of example and not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, or optical disc storage, magnetic disk storage, or other magnetic storage devices, flash memory, or any other medium capable of storing desired program code in the form of instructions or data structures that can be accessed by a computer. Furthermore, any connection may be appropriately referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using a wired (e.g., coaxial cable, fiber optic cable, twisted pair) or wireless (e.g., infrared, radio, and microwave) connection, that wired or wireless connection is included in the definition of a medium. However, it should be understood that computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but rather refer to non-transient tangible storage media.

[0127] Instructions can be executed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, graphics processing units (GPUs), application-specific integrated circuits (ASICs), field-programmable arrays (FPGAs), quantum processors, or other equivalent integrated or discrete logic circuits. Therefore, the terms "processor" or "processing circuit" as used herein can each refer to any of the foregoing structures or any other structure suitable for implementing the described techniques. Furthermore, in some embodiments, the described functionality can be provided within dedicated hardware and / or software modules. Moreover, these techniques can be fully implemented within one or more circuit or logic elements.

[0128] The techniques disclosed herein can be implemented in a variety of devices or apparatuses, including, to appropriate extent, wireless handheld devices, mobile or non-mobile computing devices, wearable or non-wearable computing devices, integrated circuits (ICs), or a set of ICs (e.g., chipsets). Various components, modules, or units are described in this disclosure to emphasize functional aspects of a device configured to perform the disclosed techniques, but are not necessarily required to be implemented through different hardware units. Rather, as described above, various units may be combined in hardware units or provided by a collection of interoperable hardware units (including one or more processors as described above) combined with appropriate software and / or firmware.

Claims

1. A method for managing a wireless network, comprising: Network data associated with the first wireless network is collected by the computing system; The computing system collects network data associated with the second wireless network, wherein the first wireless network and the second wireless network have overlapping coverage areas, and wherein the first wireless network and the second wireless network are different wireless network types; The computing system identifies user equipment attached to the first wireless network and located in the overlapping coverage area based on network data associated with the first wireless network, wherein the user equipment can also be attached to the second wireless network; The computing system predicts network conditions affecting the user equipment based on both network data associated with the first wireless network and network data associated with the second wireless network; and The computing system performs actions to remedy the network conditions affecting the user equipment based on the predicted network conditions.

2. The method according to claim 1, wherein, The first wireless network is a cellular network, and the second wireless network is a Wi-Fi wireless network, and the prediction of the network conditions includes: Predict the network condition before it occurs.

3. The method according to claim 1, wherein, The first wireless network is a Wi-Fi wireless network; and the second wireless network is a cellular network, and the prediction of the network conditions includes: The predicted network condition has already occurred.

4. The method according to claim 1, wherein, The predicted network conditions include: It is predicted that there is network congestion in the first wireless network and no network congestion in the second wireless network.

5. The method according to claim 4, wherein, Performing the actions to remedy the network congestion in the first wireless network includes: Disconnect the user equipment from the first wireless network; and This enables the user equipment to attach to the second wireless network.

6. The method according to claim 5, further comprising: The computing system monitors the user equipment's experience during the time period when the user equipment is attached to the first wireless network and then to the second wireless network.

7. The method according to any one of claims 1 to 6, in, Predicting the network conditions includes: predicting data usage anomalies associated with the user equipment; and The action taken to remedy the network condition includes making configuration changes to the user equipment.

8. The method according to any one of claims 1 to 6, in, Predicting the network condition includes: predicting network attachment anomalies associated with the user equipment; and The action taken to remedy the network condition includes making configuration changes to the user equipment.

9. The method according to any one of claims 1 to 6, wherein, The predicted network conditions include: Output a user interface that provides information about the network conditions affecting the user equipment.

10. The method according to any one of claims 1 to 6, wherein, Performing the actions to remedy the network condition includes: The action will be performed automatically.

11. The method according to any one of claims 1 to 6, wherein, Performing the actions to remedy the network condition includes: The action is performed in response to input authorizing the action.

12. The method according to any one of claims 1 to 6, wherein, The user equipment is a first user equipment, and the method further includes: The computing system identifies a second user equipment attached to the second wireless network and located within the overlapping coverage area, based on network data associated with the second wireless network; and The computing system predicts the network conditions affecting the second user equipment based on both network data associated with the first wireless network and network data associated with the second wireless network.

13. The method of claim 12, further comprising: The computing system performs actions to remedy the network conditions affecting the second user equipment based on the predicted network conditions.

14. A computing system comprising processing circuitry and storage devices, wherein, The processing circuit can access the storage device, and the processing circuit is configured to: Collect network data associated with the first wireless network; Collect network data associated with a second wireless network, wherein the first wireless network and the second wireless network have overlapping coverage areas, and wherein the first wireless network and the second wireless network are different wireless network types; Based on network data associated with the first wireless network, user equipment attached to the first wireless network and located in the overlapping coverage area is identified, wherein the user equipment can also be attached to the second wireless network; Based on both network data associated with the first wireless network and network data associated with the second wireless network, the network conditions affecting the user equipment are predicted; and Based on the predicted network conditions affecting the user equipment, actions are taken to remedy the network conditions affecting the user equipment.

15. The computing system according to claim 14, wherein, The first wireless network is a cellular network, and the second wireless network is a Wi-Fi wireless network, and the processing circuit is further configured to: In order to predict the network conditions, Predict the network condition before it occurs.

16. The computing system according to claim 14, wherein, The first wireless network is a Wi-Fi wireless network; and the second wireless network is a cellular network; and the processing circuit is further configured to: in order to predict the network conditions. The predicted network condition has already occurred.

17. The computing system according to claim 14, wherein, In order to predict the network conditions, the processing circuit is further configured to: It is predicted that there is network congestion in the first wireless network and no network congestion in the second wireless network.

18. The computing system according to claim 17, wherein, In order to perform the action to remedy the network congestion in the first wireless network, the processing circuit is further configured to: The user equipment is disconnected from the first wireless network and then attached to the second wireless network.

19. The computing system according to any one of claims 14 to 18, in, To predict the network conditions, the processing circuitry is further configured to: predict network attachment anomalies associated with the user equipment; and In order to perform the action to remedy the network condition, the processing circuit is further configured to: make configuration changes to the user equipment.

20. A computer-readable storage medium encoded with instructions for causing one or more programmable processors to be configured to perform the method according to any one of claims 1 to 13 or to be configured as a computing system according to any one of claims 14 to 19.

Images