Beamforming optimization for adaptation to environmental changes and RF consumption modes

Abstract

A data communication network (100, 200) comprises: a data communication node (120) configured to establish a data connection with a user equipment device (160) within an RF coverage area; an imaging device (130) configured to provide image information for the RF coverage area; and an information processing system (300). The information handling system (110, 300) receives RF coverage information from the data communication node (120), receives first image information from the imaging device (130), determines a first RF coverage map of the RF coverage area based on the RF coverage information and the image information, provides a first bandwidth allocation to the data communication node (120) based on the first RF coverage map, and transmits the first bandwidth allocation to the data communication node (120). Receiving second image information from the imaging device (130), determining that the first RF coverage map has become a second RF coverage map based on a difference between the first image information and the second image information, and providing a second bandwidth allocation to the data communication node (120) based on the second RF coverage map.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Patent Application No. 18 / 187,903, filed March 22, 2023, entitled “BEAMFORMING OPTIMIZATION TO ADAPTTO ENVIRONMENTAL CHANGES AND RF CONSUMPTION PATTERNS”, which has been assigned to the current applicant of this application and is incorporated herein by reference in its entirety.

[0002] U.S. Patent Application No. 18 / 187,903 is a continuation-in-part of U.S. Patent Application No. 17 / 711,531, filed April 1, 2022, entitled “REAL-TIME 3DLOCATION SERVICE FOR DETERMINISTIC RF SIGNAL DELIVERY” and U.S. Patent Application No. 17 / 711,577, filed April 1, 2022, entitled “REAL-TIME 3D TOPOLOGY MAPPING FOR DETERMINISTIC RF SIGNAL DELIVERY”, the full disclosure of which is hereby expressly incorporated by reference.

[0003] The subject matter of co-pending U.S. Patent Application No. 18 / 187,944, filed March 22, 2023, entitled “Pattern Learning to Eliminate Repetitive Compute Operations in a Data Communications Network,” the disclosure of which is hereby incorporated by reference. Technical Field

[0004] This disclosure relates generally to communication systems, and more specifically to beamforming optimization for adapting to environmental changes and RF consumption patterns. Background Technology

[0005] As the value and use of information continue to grow, individuals and businesses seek additional ways to process and store information. One option is an information processing system. Information processing systems typically process, compile, store, and / or communicate information or data for business, personal, or other purposes. Because technology and information processing needs and requirements can vary across different applications, information processing systems can also vary in terms of what information is processed, how it is processed, how much information is processed, stored, or communicated, and how quickly and efficiently it can be processed, stored, or communicated. Variations in information processing systems allow them to be general-purpose or configured for specific users or purposes (such as financial transaction processing, scheduling, enterprise data storage, or global communications). Furthermore, information processing systems can include a variety of hardware and software resources that can be configured to process, store, and communicate information, and can include one or more computer systems, data storage systems, and networked systems. Summary of the Invention

[0006] A data communication network may include: a data communication node configured to establish a data connection with a user equipment device within an RF coverage area; an imaging device configured to provide image information for the RF coverage area; and an information processing system. The information processing system may receive RF coverage information from the data communication node, receive first image information from the imaging device, determine a first RF coverage map of the RF coverage area based on the RF coverage information and the image information, provide a first bandwidth allocation to the data communication node based on the first RF coverage map, receive second image information from the imaging device, determine that the first RF coverage map has changed to a second RF coverage map based on the difference between the first image information and the second image information, and provide a second bandwidth allocation to the data communication node based on the second RF coverage map. Attached Figure Description

[0007] It should be understood that, for the sake of simplicity and clarity, the elements shown in the accompanying drawings are not necessarily drawn to scale. For example, the dimensions of some elements are enlarged relative to others. The accompanying drawings illustrate and describe embodiments incorporating the teachings of this disclosure, in which: Figure 1 This is a diagram of a data communication network according to an embodiment of this disclosure; Figure 2 It is shown Figure 1 A block diagram of the cluster controller for a data communication network; Figure 3 This is a block diagram illustrating a generalized information processing system according to another embodiment of the present disclosure; Figure 4 yes Figure 1A diagram of a data communication network; and Figure 5 yes Figure 1 Another illustration of a data communication network.

[0008] In different accompanying drawings, the same reference numerals are used to indicate similar or identical items. Detailed Implementation

[0009] The following description, provided in conjunction with the accompanying drawings, aids in understanding the teachings disclosed herein. The discussion below focuses on specific implementations and embodiments of the teachings. This focus is intended to aid in describing the teachings and should not be construed as limiting the scope or applicability of the teachings. However, other teachings may of course be used in this application as well. These teachings may also be used in other applications and with several different types of architectures, such as distributed computing architectures, client / server architectures, or middleware server architectures, and associated resources.

[0010] Figure 1 A data communication network 100 is illustrated, comprising a cluster controller 110, one or more data communication nodes 120, and one or more imaging devices 130. The data communication network 100 represents a distributed communication network, such as a cellular network for communicating with a distributed group of user equipment (UEs) 160. For example, the data communication network 100 may represent a fifth-generation (5G) cellular network, a WiFi network, a wireless wide area network (WAN), or another type of data communication network. The UE 160 may represent a 5G-enabled mobile cellular device, an Internet of Things (IoT) device, a machine-to-machine interconnect device, etc. In a particular embodiment, the data communication node 120 represents a cellular communication node and is operated, managed, and maintained according to a specific cellular infrastructure standard, such as the General Public Radio Interface (CPRI) standard, wherein the data communication node includes: a radio equipment (RE) component configured to provide wireless data communication according to a specific radio data protocol; and a radio equipment control (REC) component configured to control the RE and provide connectivity to a wider cellular data network infrastructure.

[0011] Details of data communication via data communication networks, and particularly wireless communication via, for example, cellular data communication networks, are known in the art and will not be described further herein unless required to illustrate the current implementation. UE 160 may refer to any device configured to communicate within data communication network 100 and, in particular, with node 120. For example, UE 160 may include a mobile phone, tablet device, computer device (such as a laptop or desktop computer), mobile device (such as a vehicle-based communication system), IoT device, etc.

[0012] Each node 120 is connected to a cluster controller 110. The cluster controller 110 operates to provide monitoring, management, and maintenance services to the nodes 120 as needed or desired. The cluster controller 110 can be understood as being located near the nodes 120, or as being located at the central location of the data communication network 100 (such as a data center associated with the data communication network), and the functions and characteristics of the cluster controller can be performed as needed or desired by a single public information processing system, or by one or more distributed information processing systems. Monitoring, management, and maintenance of data communication networks are known in the art and will not be further described herein unless required to illustrate the current implementation.

[0013] The data communication network 100 is configured such that one or more of the nodes 120 include an integrated or stand-alone imaging device 130. The data communication network 100 is also configured to include one or more additional imaging devices 130 that are not directly associated with any particular node but operate in stand-alone capacity. Whether associated with a node or operating as a stand-alone device, the imaging device 130 refers to a device positioned and configured to provide still images and video surveillance of the RF coverage area of ​​the data communication network 100. The imaging device 130 may include visible light detection devices, invisible light detection devices (such as infrared cameras, lidar systems, etc.), radar imaging devices, acoustic imaging devices, or other types of devices that can be used to generate topology information, as described below. In either case, the cluster controller 110 operates to provide monitoring, management, and maintenance services to the imaging device 130 as needed or desired.

[0014] In a particular implementation, cluster controller 110 operates to receive image information from the field of view of imaging device 130 and RF coverage information from node 120. Cluster controller 110 uses the image information and RF coverage information to synthesize a three-dimensional (3D) map of the physical topology of the RF coverage area of ​​data communication network 100. Cluster controller 110 then associates the connection status of node 120 with various components of UE 160 connected to data communication network 100 within the field of view of each of the imaging devices with the 3D map of the physical topology of the RF coverage area. Specifically, cluster controller 110 determines when a particular component of UE 160 experiences weakened or disconnected connectivity and associates the location where the UE experiences weakened or disconnected connectivity with the 3D map of the physical topology of the RF coverage area. In this way, cluster controller 110 operates to identify features 150 within the 3D map of the physical topology of the RF coverage area that may weaken or block the connection between a particular node 120 and UE 160. Examples of rendering the 3D map of the physical topology may include associating multiple imaging inputs 210 using neural radiation field (NeRF) algorithms, structure-of-motion (SfM) algorithms, etc.

[0015] For example, the cluster controller 110 may operate to determine that a particular node 120 is not currently connected to the UE 160, and associate image information provided by imaging devices 130 within the RF coverage area of ​​that node, including any imaging devices associated with the node and any independent imaging devices that cover the RF coverage area of ​​the node as their field of view. In this way, the cluster controller 110 can synthesize a 3D map of the RF coverage area of ​​each of the nodes 120 into a 3D map of feature 150 within the RF coverage area of ​​the data communication network 100.

[0016] When a specific component of UE 160 is connected to a specific node 120, this connection is maintained by said node until a time when the connection is interrupted, such as when the UE moves out of the node's range or enters the node's coverage blind spot. However, node 120 typically does not know when the connection is lost, and when a component of UE 160 loses coverage, the UE typically initiates a process to initiate other connection options with the first node 120 or establish a new connection with another node 120. That is, from the node's perspective, the connection between UE 160 and node 120 is typically reactive. However, from the UE 160's perspective, this reactive approach can lead to poor performance because of the poor link performance between detecting the loss of connection with the first node 120 and establishing a new connection with the second node 120.

[0017] When establishing and maintaining the connection between the components of node 120 and UE 160, a typical node in a data communication network will utilize a multiple-input multiple-output (MIMO) antenna array to provide communication signals to the UE, and will attempt to provide the communication signals by beamforming the signal with the antenna array to maximize the signal strength received by the UE, while minimizing the node's power output to the communication signal. The node may employ various algorithms and feedback from the UE to adjust the beamforming activity to maintain optimal signal strength between the node and the UE. Details regarding the establishment, maintenance, and optimization of data communication connections between nodes in a data communication network and UEs within the data communication network are known in the art and will not be further described herein unless required to illustrate the current implementation.

[0018] In a particular implementation, the cluster controller 110 operates to correlate image information from the imaging device 130 with beamforming information from the node 120 to identify and manage connection targets between the node and various UEs 160 within the RF coverage area of ​​the data communication network 100. The cluster controller 110 also utilizes motion information to predict the future movement of the UEs 160 within the data communication network 100.

[0019] The cluster controller 110 operates to proactively guide nodes 120 associated with specific components of UE 160 to provide beamforming parameters to improve communication signals to the UE and increase the efficiency of node delivery of communication signals to the UE. Furthermore, utilizing a 3D map of the RF coverage area of ​​node 120, the cluster controller 110 operates to predict when components of UE 160 will enter the blind zone or high attenuation zone of a specific node and proactively switches communication with that UE to another node with a suitable RF path to that UE. In this way, degradation of the connection between components of UE 160 and the data communication network 100 is mitigated, and the user may not experience coverage interruptions because the data communication network 100 proactively manages the connection between node 120 and UE 160 by changing beamforming parameters.

[0020] In another implementation, cluster controller 110 operates to proactively allocate data bandwidth among nodes 120 based on spatial insights from visual information. For example, if the RF coverage area of ​​a particular node 120 appears to be sparsely populated by UEs 160, while another node appears to be densely populated by UEs, cluster controller 110 may operate to allocate more data bandwidth to the densely populated node (if there is still a line of sight to be directed to the UEs associated with the densely populated node). Furthermore, based on historical information, future bandwidth may be prepared for other nodes 120 within the data communication network 100. For example, consider an event venue that is empty after an event. It should be understood that UEs 160 associated with event participants may expect to move from the event venue to a nearby parking garage and then to an adjacent road, and cluster controller 110 may operate to shift backend data bandwidth to the core network between the associated nodes 120 near the venue, the parking garage, and the adjacent road to meet the expected usage pattern. In another implementation, cluster controller 110 operates to associate a user of a particular UE 160 with its associated Service Level Agreement (SLA) and allocate data bandwidth to the UE accordingly.

[0021] In a particular implementation, cluster controller 110 utilizes artificial intelligence / machine learning (AI / ML) algorithms to analyze image information for monitoring and maintaining a 3D map. For example, while feature 150 can generally be understood as representing a fixed feature, such as a building or other fixed signal obstruction, using AI / ML algorithms, cluster controller 110 can add real-time RF path obstacles to the 3D map of the RF coverage area of ​​node 120. Consider a large moving obstacle (such as a bus or large truck) moving through the RF coverage area of ​​a particular node 120. Cluster controller 110 is operable to improve real-time maintenance of the connection, such as blind spot detection, rapidly changing RF environments, and beamforming activities, to better account for moving obstacles in the RF path. It should be further understood that other real-time RF path obstacles, such as human bodies or animals within the 3D map, can be identified. Furthermore, using AI / ML algorithms, cluster controller 110 is operable to predict processing needs for the RF coverage area of ​​node 120 and increase or decrease backend processing power to meet changing demand conditions.

[0022] As described herein, the functions and features of cluster controller 110 may be instantiated in hardware, in software or code, or in a combination of hardware and code configured to perform the described functions and features. Furthermore, the functions and features may be provided at a single location or by a single device (such as an information processing system), or by two or more devices (such as two or more information processing systems) at two or more locations. One or more of the functions and features described herein may each be performed by different information processing systems, and any particular function or feature may be distributed across two or more information processing systems as needed or desired. Furthermore, as described herein, the functions and features of cluster controller 110 can be understood as being provided at any network level as needed or desired.

[0023] For example, if the data communication network 100 comprises separate groups of nodes 120, each group routing through a common access switch, where data flows from the separate access switch groups are aggregated by a common aggregator, and where the processing needs of the aggregator groups are handled by the core data processing network, then the functionality and features of the cluster controller 110 may be provided, as needed or desired, by one or more of the access switches, aggregators, or the core network. Therefore, it might be considered desirable to perform graph synthesis at the core network, where access times are typically longer but data processing capabilities are typically greater, while it might be considered desirable to perform UE motion tracking and connection handover at a processing level closer to the nodes, where access times are typically shorter.

[0024] Figure 2 The cluster controller 110 is shown in more detail. The cluster controller 110 is configured to receive imaging input 210 from the imaging device 130. The cluster controller 110 operates to process the imaging input and control the operation of nodes in the data communication network 100, which includes node 120. The cluster controller 110 further operates to provide nodes with pre-configuration 230, resource tracking 232 for UEs within the data communication network 100, including UE 160, and RF power management 234 for the nodes.

[0025] Imaging input 210 represents the output from imaging device 130 and may include any still or moving imaging format as may be known in the art, including proprietary still or moving imaging formats. When a particular imaging device 130 is configured for still images (i.e., a camera device), the image will be understood as being received by the cluster controller based on various timestamps (t0, t1, t2, ...) associated with the actual time of still image capture. Still image imaging device 130 may be configured to capture images at a predetermined timetable, such as every five seconds or every ten seconds, or may be configured to capture images based on various inputs of the imaging device (such as based on motion sensors, etc.). Video image imaging device may be configured to provide continuous streaming video images, or may be configured to provide video images based on various timestamps (t0, t1, t2, ...). As needed or desired, imaging device 130 may be configured to capture images in the visible light spectrum, in the near-visible light spectrum, or in other invisible light spectra.

[0026] The cluster controller 110 includes a graph synthesis module 220, a motion prediction module 222, a blind spot prediction module 224, an RF coverage mapping module 226, and an optimization / learning module 228. The graph synthesis module 220 receives imaging input 210 and synthesizes a 3D graph of the RF coverage area of ​​the data communication network 100 as described above. It should be understood here that inputs from two or more imaging devices 130 will be used to synthesize a 3D graph of the RF coverage area of ​​the data communication network 100, and the more imaging device inputs received by the cluster controller 110, the better and more accurate the 3D graph synthesized by the graph synthesis module 220 will be. The cluster controller 110 also receives coverage information from nodes 120. For example, the cluster controller 110 may receive an RF signal strength map 226 of the RF coverage area associated with each node 120, including default beamforming settings, coverage angle, RF signal power settings, etc. Here, the blind spot prediction module 224 operates to associate the synthesized 3D map with the received coverage information to generate a baseline RF coverage map, which predicts the presence of feature 150, which is understood to present obstacles that attenuate the RF signal between node 120 and UE 160.

[0027] In a particular implementation, the baseline RF coverage map is synthesized based on real-time information from imaging device 130. Specifically, it should be understood that a particular RF coverage area of ​​a particular node 120 may be continuously filled by one or more UEs 160 and other objects within the field of view of imaging device 130, which may make the generation of the baseline RF coverage map difficult. However, here, the graph synthesis module 220 may utilize the optimization / learning module 228 to create a baseline RF coverage map based on responses learned from the RF coverage area, assuming that the RF coverage area is completely free of UEs 160 and other objects. Furthermore, the graph synthesis module 220 operates to periodically update the baseline RF coverage map based on changing conditions within the RF coverage area. For example, if the RF coverage area represents an activity area, the presence of a moving truck in the loading / unloading area may represent a temporary obstacle within the coverage area of ​​node 120's line of sight to the loading / unloading area. Or, if the RF coverage area represents an office space, the reorganization of cubicles within the office space may affect the updated coverage map of the office area.

[0028] The cluster controller 110 also utilizes artificial intelligence / machine learning (AI / ML) algorithms embodied in the optimization / learning module 228 to analyze image information to monitor and maintain the baseline RF coverage map. For example, while feature 150 can generally be understood as representing fixed or semi-permanent features, such as buildings, parked vehicles, or other fixed signal obstacles, using AI / ML algorithms, the cluster controller 110 can add real-time RF path obstacles to the baseline RF coverage map of the RF coverage area of ​​node 120. Consider large moving obstacles (such as buses or large trucks) moving through the RF coverage area of ​​a particular node 120. The cluster controller 110 is operable to improve real-time maintenance of the connection, such as blind spot detection, rapidly changing RF environments, and beamforming activities, to better account for moving obstacles in the RF path. Furthermore, using AI / ML algorithms, the cluster controller 110 is operable to predict processing needs for the RF coverage area of ​​node 120 and increase or decrease backend processing power to meet changing demand conditions.

[0029] This baseline RF coverage map can be utilized in conjunction with the movement of objects within the RF coverage area, as determined by the motion prediction module 222. Therefore, the movement of vehicles, people, etc., through the RF coverage area can be predicted. The motion detection module 222 further operates to identify the speed and trajectory of objects, thereby distinguishing people from vehicles or other objects within the RF coverage area. Then, based on graph information from the graph synthesis module 220 and object and motion information from the object detection module 222, the blind spot prediction module 224 operates to predict the coverage blind spot of each of the nodes 120. The blind spot can be combined with information from the predetermined RF coverage map module 226 to predict the real-time blind spot of each of the nodes 120.

[0030] Returning to motion prediction module 222, the movement of objects through the RF coverage area of ​​node 120 is combined with information related to the beamforming state of UE 160 within the RF coverage area of ​​each node. Motion prediction module 222 further operates to identify objects associated with the user of UE 160 within the RF coverage area of ​​each node 120, as well as the user's speed and trajectory. Blind spot prediction module 224 further operates to associate the movement of UE 160 with the identified blind spots to determine in advance when a particular UE is expected to lose connection with a particular node 120, and further operates to determine the next optimal node to take over the UE. Optimization / learning module 228 utilizes various AI / ML algorithms to better predict the occurrence of signal blocking obstacles and the expected movement of the user of connected UE 160. As described above, cluster controller 110 ultimately operates to guide the activity of node 120 to proactively maintain optimal connectivity for UEs within the RF coverage area of ​​data communication network 100 by implementing node pre-configuration 230, UE resource tracking 232, and RF power management.

[0031] Figure 4 It shows that in comparison Figure 1 The data communication network 100 is shown at a later time. At timestamp (t3), a new feature 450 is detected within the RF coverage area, and the cluster controller 110 synthesizes a modified baseline RF coverage map of the RF coverage area of ​​node 120 based on the newly determined image data from imaging device 130, as described above. Furthermore, the cluster controller 110 operates to calculate the spatial distribution of the effective RF signal strength based on the attenuation from feature 450, and determines a new baseline RF coverage map of the RF coverage area.

[0032] In addition to determining a new baseline RF coverage map based on feature 450 to define the RF coverage area, the cluster controller 110 operates to provide node 120 with modified beamforming settings to achieve minimal RF coverage within the RF coverage area based on the new baseline RF coverage map, taking into account the attenuation provided by the new feature. Furthermore, the cluster controller 110 operates to determine usage patterns within the RF coverage area based on the new baseline RF coverage map. For example, if feature 450 represents a commercial establishment (such as a coffee shop), the cluster controller 110 can determine the usage patterns of UEs within the RF coverage area, such as anticipating a "morning rush" at the coffee shop at timestamp (t4), or if the feature represents an office building, the cluster controller can determine the usage patterns of UEs entering in the morning and leaving in the evening. Furthermore, the cluster controller 110 operates to provide node 120 with time-based modifications to the beamforming settings to take into account the UE usage patterns, thereby reducing power consumption within the data communication network 100 during periods of less use and resolving data bandwidth congestion during periods of higher use.

[0033] At a later timestamp (t5), another new feature 452 is detected to have been built within the RF coverage area, and the cluster controller 110 synthesizes a new modified baseline RF coverage map of the RF coverage area of ​​node 120 based on the newly determined image data from imaging device 130. The cluster controller 110 also provides node 120 with the newly modified beamforming settings, determines the UE usage patterns within the modified baseline RF coverage map, and provides the node with time-based modifications to the beamforming settings. Furthermore, since feature 452, representing, for example, a new office building, may be expected to result in additional UEs operating within the RF coverage area, the cluster controller 110 operates to suggest adding a new node 420 and a new imaging device 430 to provide additional RF coverage and extend the RF coverage area to include feature 452.

[0034] When synthesizing a modified baseline RF coverage map, the cluster controller 110 is operable to periodically (e.g., daily) resynthesize the baseline RF coverage map. The cluster controller 110 may determine times when the UEs of the data communication network 100 have low usage, such as early morning hours with minimal vehicle and pedestrian traffic, so that the imaging data primarily represents features 150, 450, and 452. Alternatively, the cluster controller 110 is operable to implement a volume change threshold such that when the cluster controller detects a change in a feature within the baseline RF coverage map exceeding the volume change threshold, the change triggers the resynthesis of the baseline RF coverage map. In either case, the addition or removal of features within the RF coverage area can be readily accounted for in the newly synthesized baseline RF coverage map.

[0035] Figure 5A data communication network 100 according to a specific embodiment of this disclosure is illustrated. According to the various embodiments described herein, a cluster controller 110 operates to direct beamforming activities of node 120 to a target UE 160 for deterministic signal delivery. Therefore, the cluster controller 110 operates to calculate and analyze the trajectories of UE 160 operating within the RF coverage area and to coordinate beam configurations and smooth handovers of various UEs between nodes 120.

[0036] The inventors of this disclosure have understood that the movement of each UE 160 within the RF coverage area is unique, such as originating from different locations, traveling at different speeds, taking different paths, etc. It has also been understood that the movement of UE 160 can be categorized into relatively few predictable patterns attributable to the UE. For example, pedestrians are typically understood to walk on a sidewalk along one of two main directions (e.g., uphill or downhill) in a relatively straight path, and the main differences between pedestrians are generally related to their speed (e.g., strolling, walking, running, etc.). Therefore, the beamforming settings for each node-UE connection can be understood to be highly predictable and may not require extensive analysis by the cluster controller to predict possible paths or speeds. Furthermore, the location of handover points can be easily determined considering the speed of a particular UE.

[0037] Since UE movement is typically linear, once the cluster controller 110 determines the most suitable algorithm for the UE's movement, it can offload that algorithm to a processing node closer to the RF coverage area. In other words, the cluster controller 110 can represent the back-end functionality of the data communication network 100. The data communication network 100 may include additional processing nodes between the cluster controller and node 120. In this case, the back-end processing capabilities of the cluster controller 110 can be best utilized to provide AI / ML analysis of the UE 160's movement within the RF coverage area to find the most suitable beamforming algorithm, and then pass these algorithms to the processing node closer to node 120 to guide the node's actual beamforming activities.

[0038] In another implementation, the optimization / learning module 228 trains an AI / ML algorithm based on the behavior of multiple UEs and associated handovers between nodes 120. The optimization / learning module 228 operates to identify the trajectories of various UEs and the volume occupied by a UE or UE cluster. For example, the optimization / learning module 228 can be operated to distinguish individual UEs (such as those that may occupy 0.5 to 1.5 m). 3 A pedestrian of that size, or possibly occupying 10 to 30 meters. 3 The volume of a delivery truck), multi-point UEs (such as a set of a certain number of UEs that all share a common trajectory and may occupy 10 to 20m)3 (e.g., a bus with a full load of UEs). The cluster controller 110 operates to determine the optimal handover location, associated beamforming settings, etc. Furthermore, the cluster controller 110 operates to select the optimal node 120 to receive the handover based on the data traffic handled by each node. For example, where a bus full of UEs would typically be handed over to a specific node 120, the cluster controller 110 may determine that the specific node is currently experiencing greater bandwidth usage, and therefore the cluster controller may select a different node with greater available bandwidth to hand over the UE to that node.

[0039] It should be understood that once the optimization / learning module 22 has trained the AI / ML algorithm, the need for extensive processing power to predict common paths for UEs within the coverage area will be significantly reduced. Furthermore, once the AI / ML algorithm is trained, the most frequently taken paths can be captured as a separate algorithm requiring less processing power, and this separate algorithm can be delivered to node 120 or other intermediate processing centers as needed or desired. In this way, the utilization of processing resources throughout the data communication network 100 can be improved, and bandwidth utilization between the cluster controller 110 and node 120 can be reduced.

[0040] In another implementation, the cluster controller 110 operates to assess the energy usage of the data communication network 100 and, in particular, node 120, and then manages handover of UEs within the RF coverage area to minimize energy consumption by the data communication network. For example, the optimization / learning module 228 is operable to learn from imaging information provided by the imaging device 130 that usage patterns within the RF coverage area are highly dependent on the time of day and a particular day of the week. The cluster controller 110 operates to allocate lower bandwidth to node 120 during identified periods of less usage, thereby conserving radio energy by reducing the number of RF channels or shutting down unused nodes, and freeing up processing resources of the data communication network 100 for other tasks, such as routine data backups.

[0041] Figure 5 Several exemplary UEs (UE1 to UE4) and their corresponding trajectories over the RF coverage area of ​​data communication network 100 are further illustrated. UE1 represents a pedestrian crossing a sidewalk. Since a pedestrian's trajectory on a sidewalk is typically a straight path, cluster controller 110 operates to anticipate UE1's path based on the learning described above and to set UE1's handover position (L1) based on the learned algorithm. The precise location of the handover position (L1) can be determined based on the pedestrian's speed (e.g., walking, running, etc.). Furthermore, since the boundaries of the sidewalk are known from image data and the learned pedestrian behavior, cluster controller 110 redirects beamforming settings to node 120 to remain within the sidewalk.

[0042] UE2 represents a vehicle crossing the road. Since the trajectory of a vehicle on the road is typically a straight path, the cluster controller 110 operates to anticipate the path of UE2 based on the learning described above, and sets the switching position (L2) of UE2 based on the learned algorithm. The switching position (L2) is typically earlier than the switching position (L1) of UE1 because vehicle speeds are generally greater than pedestrian speeds. However, based on image data, the cluster controller 110 can determine that vehicle traffic on the road is actually slower than pedestrian traffic on the sidewalk, for example, because this is associated with a "peak hour" on the road. The switching position (L2) associated with UE2 may actually be later than the switching position (L1) associated with UE1. Furthermore, as described above, the precise location of the switching position (L2) can be determined based on vehicle speed and the road boundaries can be learned from image data and learned pedestrian behavior.

[0043] In a particular implementation, image information from imaging device 130 can be advantageously used to predict changes in the trajectory of the UE within the RF coverage area of ​​data communication network 100. For example, UE3 represents a pedestrian crossing a sidewalk. Therefore, cluster controller 110 operates to anticipate the path of UE3 based on the learning described above, and typically sets the handover position (L1) of UE3 based on the learned algorithm. However, based on image information from imaging device 130, cluster controller 110 operates to detect that the pedestrian has turned from the sidewalk into an alley. In this case, cluster controller 110 provides a modified handover position (L3) that takes into account the new path through the alley. Trajectories of pedestrians and vehicles crossing alleys can be learned, as described above, and therefore changes in handover position (L3) may be accompanied by different algorithms optimized for movement through alleys used for beamforming settings. In another example, UE4 represents a bus crossing a road and turning into an alley. The bus may include multiple UEs. Therefore, based on a combination of image information and knowledge that multiple UEs are moving within the bus, cluster controller 110 operates to provide an earlier handover position (L4) for UE4.

[0044] Figure 3A generalized embodiment of an information processing system 300 is illustrated. For the purposes of this disclosure, the information processing system may include any tool or set of tools that can be used to calculate, classify, process, transmit, receive, retrieve, initiate, convert, store, display, indicate, detect, record, reproduce, dispose of, or utilize information, intelligence, or data of any form for commercial, scientific, control, entertainment, or other purposes. For example, the information processing system 300 may be a personal computer, laptop computer, smartphone, tablet device, or other consumer electronic device, web server, network storage device, switching router, or other network communication device, or any other suitable device, and may vary in size, shape, performance, functionality, and price. Furthermore, the information processing system 300 may include processing resources for executing machine-executable code, such as a central processing unit (CPU), a programmable logic array (PLA), an embedded device (such as a system-on-a-chip (SoC)), or other control logic hardware. The information processing system 300 may also include one or more computer-readable media for storing machine-executable code such as software or data. Additional components of the information processing system 300 may include one or more storage devices for storing machine-executable code, one or more communication ports for communicating with external devices, and various input and output (I / O) devices, such as a keyboard, mouse, and video display. The information processing system 300 may also include one or more buses operable to transfer information between various hardware components.

[0045] Information processing system 300 may include one or more of the means or modules described below, and operates to perform one or more of the methods described below. Information processing system 300 includes processors 302 and 304, input / output (I / O) interfaces 310, memory 320 and 325, a graphics interface 330, a Basic Input / Output System / General Purpose Extensible Firmware Interface (BIOS / UEFI) module 340, a disk controller 350, a hard disk drive (HDD) 354, an optical disk drive (ODD) 356, a disk emulator 360 connected to an external solid-state drive (SSD) 364, an I / O bridge 370, one or more expansion resources 374, a Trusted Platform Module (TPM) 376, a network interface 380, a management device 390, and a power supply 395. Processors 302 and 304, I / O interface 310, memory 320 and 325, graphics interface 330, BIOS / UEFI module 340, disk controller 350, HDD 354, ODD 356, disk emulator 360, SSD 364, I / O bridge 370, expansion resources 374, TPM 376, and network interface 380 work together to provide the host environment for information processing system 300, which operates to provide data processing functions for the information processing system. The host environment operates to execute machine-executable code, including platform BIOS / UEFI code, device firmware, operating system code, applications, programs, etc., to perform data processing tasks associated with information processing system 300.

[0046] In a host environment, processor 302 is connected to I / O interface 310 via processor interface 306, while processor 304 is connected to I / O interface 308. Memory 320 is connected to processor 302 via memory interface 322. Memory 325 is connected to processor 304 via memory interface 327. Graphics interface 330 is connected to I / O interface 310 via graphics interface 332 and provides video display output 335 to video display 334. In a particular embodiment, information processing system 300 includes separate memory dedicated to each of processors 302 and 304 via separate memory interfaces. Examples of memories 320 and 325 include random access memory (RAM) such as static RAM (SRAM), dynamic RAM (DRAM), non-volatile RAM (NV-RAM), etc.), read-only memory (ROM), another type of memory, or combinations thereof.

[0047] The BIOS / UEFI module 340, disk controller 350, and I / O bridge 370 are connected to the I / O interface 310 via I / O channel 312. Examples of I / O channels 312 include Peripheral Component Interconnect (PCI) interfaces, extended PCI (PCI-X) interfaces, high-speed PCI-Express (PCIe) interfaces, other industry-standard or proprietary communication interfaces, or combinations thereof. The I / O interface 310 may also include one or more other I / O interfaces, including Industry Standard Architecture (ISA) interfaces, Small Computer Serial Interface (SCSI) interfaces, and Inter-Integrated Circuit (I / O) interfaces. 2 C) Interfaces such as System Packet Interface (SPI), Universal Serial Bus (USB), another interface, or combinations thereof. The BIOS / UEFI module 340 includes BIOS / UEFI code operable to detect resources within the information processing system 300, provide drivers for the resources, initialize the resources, and access the resources. The BIOS / UEFI module 340 includes code operable to detect resources within the information processing system 300, provide drivers for the resources, initialize the resources, and access the resources.

[0048] Disk controller 350 includes disk interface 352 that connects the disk controller to HDD 354, ODD 356, and disk emulator 360. Examples of disk interface 352 include Integrated Drive Electronics (IDE) interface, Advanced Technology Accessories (ATA) interface (such as Parallel ATA (PATA) or Serial ATA (SATA) interface), SCSI interface, USB interface, proprietary interface, or combinations thereof. Disk emulator 360 allows SSD 364 to be connected to information processing system 300 via external interface 362. Examples of external interface 362 include USB interface, IEEE 1394 (FireWire) interface, proprietary interface, or combinations thereof. Alternatively, solid-state drive 364 may be located within information processing system 300.

[0049] I / O bridge 370 includes peripheral interface 372 that connects the I / O bridge to expansion resource 374, TPM 376, and network interface 380. Peripheral interface 372 can be the same type of interface as I / O channel 312, or it can be a different type of interface. Therefore, when peripheral interface 372 and I / O channel 312 are of the same type, I / O bridge 370 expands the capability of the I / O channel; when they are of different types, I / O bridge converts information from a format suitable for the I / O channel to a format suitable for peripheral channel 372. Expansion resource 374 may include a data storage system, an additional graphics interface, a network interface card (NIC), a voice / video processing card, another expansion resource, or a combination thereof. Expansion resource 374 may be located on a main circuit board, on a separate circuit board or expansion card disposed within the information processing system 300, on a device external to the information processing system, or a combination thereof.

[0050] Network interface 380 refers to a NIC, which is located within information processing system 300, on the main circuit board of the information processing system, integrated into another component such as I / O interface 310, located in another suitable location, or a combination thereof. Network interface device 380 includes network channels 382 and 384, which provide interfaces to devices external to information processing system 300. In certain embodiments, network channels 382 and 384 are of a different type from peripheral channel 372, and network interface 380 converts information from a format suitable for the peripheral channel to a format suitable for external devices. Examples of network channels 382 and 384 include InfiniBand channels, Fibre Channel-type channels, Gigabit Ethernet channels, proprietary channel architectures, or combinations thereof. Network channels 382 and 384 can connect to external network resources (not shown). These network resources may include another information processing system, a data storage system, another network, a grid management system, another suitable resource, or a combination thereof.

[0051] Management device 390 refers to one or more processing devices, such as a dedicated backplane management controller (BMC), a system-on-a-chip (SoC) device, one or more associated memory devices, one or more network interface devices, a complex programmable logic device (CPLD), etc., that operate together to provide a management environment for information processing system 300. Specifically, management device 390 connects to various components of the host environment via various internal communication interfaces, such as low pin count (LPC) interfaces, inter-integrated circuit (I2C) interfaces, PCIe interfaces, etc., to provide out-of-band (OOB) mechanisms for retrieving information related to the operation of the host environment, providing BIOS / UEFI or system firmware updates, and managing non-processing components of information processing system 300 (such as system cooling fans and power supplies). Management device 390 may include a network connection to an external management system, and the management device may communicate with the management system to report status information of information processing system 300, receive BIOS / UEFI or system firmware updates, or perform other tasks for managing and controlling the operation of information processing system 300. Management device 390 can operate outside the power plane of components in the host environment, allowing it to receive power to manage information processing system 300 when the information processing system is otherwise shut down. Examples of management device 390 include commercially available BMC products or other devices operating according to the Intelligent Platform Management Initiative (IPMI) specification, Web Services Management (WSMan) interface, Redfish application programming interface (API), another Distributed Management Task Force (DMTF), or other management standards, and may include integrated Dell Remote Access Controller (iDRAC), embedded controllers (EC), etc. Management device 390 may also include associated memory devices, logic devices, security devices, etc., as needed or desired.

[0052] Although only a few exemplary embodiments have been described in detail herein, those skilled in the art will readily recognize that many modifications may be made to the exemplary embodiments without substantially departing from the novel teachings and advantages of the embodiments of this disclosure. Therefore, all such modifications are intended to be included within the scope of the embodiments of this disclosure as defined in the appended claims. In the claims, the entries for "means plus function" are intended to cover structures described herein as performing the described functions, and not only structural equivalents but also equivalent structures.

[0053] The subject matter disclosed above should be considered illustrative rather than restrictive, and the appended claims are intended to cover any and all such modifications, enhancements, and other embodiments falling within the scope of this invention. Therefore, to the fullest extent permitted by law, the scope of this invention is determined by the broadest possible interpretation of the appended claims and their equivalents, and should not be construed as limited by the foregoing detailed description.

Claims

1. A data communication network (100, 200), comprising: Multiple data communication nodes (120) are configured to establish data connections with user equipment devices (160) within a radio frequency (RF) coverage area; Multiple imaging devices (130) are configured to provide image information for the RF coverage area; as well as Information processing system (110, 300), wherein the information processing system is configured as follows: Receive RF coverage information from the data communication node (120); Receive first image information from the imaging device (130); A first RF coverage map of the RF coverage area is determined based on the RF coverage information and the image information; The first bandwidth allocation is provided to the data communication node (120) based on the first RF coverage map; Receive second image information from the imaging device (130); Based on the difference between the first image information and the second image information, it is determined that the first RF overlay map has become the second RF overlay map; as well as The second bandwidth allocation is provided to the data communication node (120) based on the second RF coverage map.

2. The data communication network (100, 200) as claimed in claim 1, wherein the first RF coverage map includes a first three-dimensional (3D) map of the RF coverage area.

3. The data communication network (100, 200) as claimed in claim 1, wherein the first RF coverage map includes a first physical feature.

4. The data communication network (100, 200) as claimed in claim 3, wherein the second RF coverage map includes a second physical feature not included in the first RF coverage map.

5. The data communication network (100, 200) as claimed in claim 3, wherein the first RF coverage map includes the second physical feature, and the second RF coverage map does not include the second physical feature.

6. The data communication network (100, 200) as claimed in claim 1, wherein the information processing system (110, 300) is further configured to: Receive third image information from the imaging device (130); and A pattern for determining the number of user equipment devices (160) in the RF coverage area based on the third image information.

7. The data communication network (100, 200) of claim 6, wherein the information processing system (110, 300) is further configured to provide a second bandwidth allocation to the data communication node (120) based on the mode.

8. The data communication network (100, 200) as claimed in claim 7, wherein when the number of the mode-indicated user equipment devices (160) increases, the second bandwidth allocation is greater than the first bandwidth allocation.

9. The data communication network (100, 200) of claim 7, wherein when the number of user equipment devices (160) indicated by the mode decreases, the second bandwidth allocation is less than the first bandwidth allocation.

10. The data communication network (100, 200) of claim 1, wherein the information processing system (110, 300) is further configured to provide a suggestion for adding a data communication node (120) to the data communication network (100, 200) based on the second RF coverage map.

11. A method comprising: Multiple data communication nodes (120) are provided in the data communication network (100, 200), the multiple data communication nodes being configured to establish data connections with user equipment devices (160) within a radio frequency (RF) coverage area; A plurality of imaging devices (130) are provided, the plurality of imaging devices being configured to provide image information for the RF coverage area; Receive RF coverage information from the data communication node (120); Receive first image information from the imaging device (130); A first RF coverage map of the RF coverage area is determined based on the RF coverage information and the image information; The first bandwidth allocation is provided to the data communication node (120) based on the first RF coverage map; Receive second image information from the imaging device (130); Based on the difference between the first image information and the second image information, it is determined that the first RF overlay map has become the second RF overlay map; as well as The second bandwidth allocation is provided to the data communication node (120) based on the second RF coverage map.

12. The method of claim 11, wherein the first RF coverage map comprises a first three-dimensional (3D) map of the RF coverage area.

13. The method of claim 11, wherein the first RF overlay map includes a first physical feature.

14. The method of claim 13, wherein the second RF overlay map includes a second physical feature not included in the first RF overlay map.

15. The method of claim 13, wherein the first RF overlay map includes the second physical feature, and the second RF overlay map does not include the second physical feature.

16. The method of claim 11, further comprising: Receive third image information from the imaging device (130); as well as A pattern for determining the number of user equipment devices (160) in the RF coverage area based on the third image information.

17. The method of claim 16, further comprising providing a second bandwidth allocation to the data communication node (120) based on the mode.

18. The method of claim 17, wherein when the number of the mode-indicated user equipment devices (160) increases, the second bandwidth allocation is greater than the first bandwidth allocation.

19. The method of claim 17, wherein when the number of user equipment devices (160) indicated by the mode decreases, the second bandwidth allocation is less than the first bandwidth allocation.

20. An information processing system (110, 300), comprising: A memory device for storing code; as well as Processor, the processor being configured to execute the code to: Radio frequency (RF) coverage information is received from multiple data communication nodes (120), which are configured to establish data connections with user equipment devices (160) within the RF coverage area; First image information is received from a plurality of imaging devices (130), the plurality of imaging devices being configured to provide image information for the RF coverage area; A first RF coverage map of the RF coverage area is determined based on the RF coverage information and the image information; The first bandwidth allocation is provided to the data communication node (120) based on the first RF coverage map; Based on the difference between the first image information and the second image information, it is determined that the first RF overlay map has become the second RF overlay map; as well as The second bandwidth allocation is provided to the data communication node (120) based on the second RF coverage map.

Images