Edge device and method for handling service for multiple service providers
A central cloud server that includes a processor which periodically obtains sensing information from a plurality of edge devices at different locations and periodically obtains beam alignment information from the plurality of edge devices. The processor correlates the obtained sensing information and the beam alignment information for different times-of-day to generate a connectivity enhanced database. The connectivity enhanced database specifies a plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships for a surrounding area of each edge device of the plurality of edge devices. The correlation is based on the obtained sensing information as input features and the beam alignment information as learning labels.
1 . A central cloud server, comprising:
a processor configured to:
periodically obtain sensing information from a plurality of edge devices at different locations;
periodically obtain beam alignment information from the plurality of edge devices; and
correlate the obtained sensing information and the beam alignment information for different times-of-day to generate a connectivity enhanced database,
wherein the connectivity enhanced database specifies a plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships for a surrounding area of each edge device of the plurality of edge devices, and
the correlation is based on the obtained sensing information as input features and the beam alignment information as learning labels.
2 . The central cloud server according to claim 1 , wherein the processor is further configured to periodically train a machine learning model for the different times-of-day on training data of the input features and parameters of the beam alignment information,
the connectivity enhanced database is generated further based on the trained machine learning model, and
the machine learning model is trained to determine patterns that map the input features to the learning labels for the correlation.
3 . The central cloud server according to claim 2 , wherein the input features comprise a distance of each edge device of the plurality of edge devices from User Equipment (UE), weather condition, a UE location, a moving direction of the UE, and a time-of-day.
4 . The central cloud server according to claim 2 , wherein the learning labels comprise initial access information, a Physical Cell Identity (PCID), a signal strength measurement of a Tx/Rx beam, a beam configuration, a transmission path, and an absolute radio-frequency channel number (ARFCN).
5 . The central cloud server according to claim 2 , wherein the machine learning model comprises a convolutional neural network (CNN).
6 . The central cloud server according to claim 1 , wherein the processor is further configured to obtain processing chain parameters from the plurality of edge devices, and
wherein the processing chain parameters are additional parameters included in the learning labels in addition to the beam alignment information.
7 . The central cloud server according to claim 6 , wherein the processor is further configured to correlate the processing chain parameters with the obtained sensing information and the beam alignment information for the different times-of-day to update the generated connectivity enhanced database.
8 . The central cloud server according to claim 1 , wherein the plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships comprise one or more of a transmit (Tx) beam information, a receive (Rx) beam information, a Physical Cell Identity (PCID), an absolute radio-frequency channel number (ARFCN), and a signal strength information associated with each of a Tx beam and an Rx beam of the plurality of edge devices.
9 . The central cloud server according to claim 1 , wherein the plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships specify, for a set of the input features for a time-of-day of the different times-of-day, a beam index to set at a first edge device for uplink communication, a specific Physical Cell Identity (PCID) that indicates a gNB to connect to, or a selection of a Wireless Communication Network, a specific beam configuration to set, or a decision to connect to a base station directly or indirectly in a Non-Line-of-Sight (NLOS) path via a second edge device in a network of the plurality of edge devices,
the decision is based on a current location of the second edge device, and
each of the first edge device and the second edge device is one of the plurality of edge devices.
10 . The central cloud server according to claim 1 , wherein the plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships specify, for a set of the input features for a time-of-day of the different times-of-day, a beam index to set at a first edge device for downlink communication, a selection of a Wireless Communication Network (WCN), a specific beam configuration to set, a power level of RF signal, or an expected time period to service one or more User Equipment (UEs) based on a current location of the first edge device, and
the first edge device is one of the plurality of edge devices.
11 . The central cloud server according to claim 1 , wherein the correlation indicates, for the input features in the sensing information, initial access information suitable for a first edge device to service one or more User Equipment (UEs) in the surrounding area, and
the first edge device is one of the plurality of edge devices.
12 . A method, comprising:
periodically obtaining, by a central cloud server, sensing information from a plurality of edge devices at different locations;
periodically obtaining, by the central cloud server, beam alignment information from the plurality of edge devices; and
correlating, by the central cloud server, the obtained sensing information and the beam alignment information for different times-of-day to generate a connectivity enhanced database,
wherein the connectivity enhanced database specifies a plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships for a surrounding area of each edge device of the plurality of edge devices, and
the correlation is based on the obtained sensing information as input features and the beam alignment information as learning labels.
13 . The method according to claim 12 , further comprising periodically training, by the central cloud server, a machine learning model for the different times-of-day on training data of the input features and parameters of the beam alignment information,
wherein the connectivity enhanced database is generated further based on the trained machine learning model, and
the machine learning model is trained to determine patterns that map the input features to the learning labels for the correlation.
14 . The method according to claim 13 , wherein the input features comprise a distance of each edge device of the plurality of edge devices from User Equipment (UE), weather condition, a UE location, a moving direction of the UE, and a time-of-day.
15 . The method according to claim 13 , wherein the learning labels comprise initial access information, a Physical Cell Identity (PCID), a signal strength measurement of a Tx/Rx beam, a beam configuration, a transmission path, and an absolute radio-frequency channel number (ARFCN).
16 . The method according to claim 13 , wherein the machine learning model comprises a convolutional neural network (CNN).
17 . The method according to claim 12 , further comprising obtaining, by the central cloud server, processing chain parameters from the plurality of edge devices,
wherein the processing chain parameters are additional parameters included in the learning labels in addition to the beam alignment information.
18 . The method according to claim 17 , further comprising correlating, by the central cloud server, the processing chain parameters with the obtained sensing information and the beam alignment information for the different times-of-day to update the generated connectivity enhanced database.
19 . The method according to claim 12 , wherein the plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships comprise one or more of a transmit (Tx) beam information, a receive (Rx) beam information, a Physical Cell Identity (PCID), an absolute radio-frequency channel number (ARFCN), and a signal strength information associated with each of a Tx beam and an Rx beam of the plurality of edge devices.
20 . The method according to claim 12 , wherein the plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships specify, for a set of the input features for a time-of-day of the different times-of-day, a beam index to set at a first edge device for uplink communication, a specific Physical Cell Identity (PCID) that indicates a gNB to connect to, or a selection of a Wireless Communication Network, a specific beam configuration to set, or a decision to connect to a base station directly or indirectly in a Non-Line-of-Sight (NLOS) path via a second edge device in a network of the plurality of edge devices,
the decision is based on a current location of the second edge device, and
each of the first edge device and the second edge device is one of the plurality of edge devices.