CN117155434A - Apparatus for use in RAN intelligent controller - Google Patents

Abstract

The present application relates to an apparatus for use in a Radio Access Network (RAN) intelligent controller (RIC), wherein the apparatus comprises a processor circuit configured to cause the RIC to: determining policy guidelines, algorithm selections, or model suggestions based on RAN measurements and location or mobility related information associated with a User Equipment (UE); and providing policy guidance, algorithm selection, or model suggestion to the E2 node for use in the RAN communicating with the UE, wherein the policy guidance is for indicating a policy for determining communication-related operations, the algorithm selection is for indicating a communication-related algorithm, and the model suggestion is for indicating one of a plurality of offline trained Artificial Intelligence (AI) or Machine Learning (ML) models to implement the communication-related algorithm.

Description

Apparatus for use in RAN intelligent controller

Technical Field

Embodiments of the present disclosure relate generally to the field of wireless communications, and more particularly, to an apparatus for use in a Radio Access Network (RAN) intelligent controller (RIC).

Background

Mobile communications have evolved from early voice systems to today's highly complex integrated communication platforms. A 5G or New Radio (NR) wireless communication system will provide various users and applications with access to information and sharing of data anytime and anywhere.

Drawings

Embodiments of the present disclosure will now be illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings in which like reference numerals refer to similar elements.

Fig. 1 illustrates a flow chart of a method for use in RIC according to some embodiments of the present disclosure.

Fig. 2 illustrates a schematic diagram of a service application running on a near RT RIC providing policy guidelines to an E2 node, according to some embodiments of the disclosure.

Fig. 3 illustrates a schematic diagram of a service application running on a near RT RIC providing model recommendations to an E2 node, according to some embodiments of the present disclosure.

Fig. 4A illustrates a schematic diagram of training multiple AI or ML models corresponding to different beamforming algorithms according to some embodiments of the present disclosure.

Fig. 4B illustrates a schematic diagram of a service application running on a near RT RIC providing a selected beamforming algorithm to an E2 node according to some embodiments of the present disclosure.

Fig. 5A illustrates a schematic diagram of training multiple AI or ML models corresponding to different backoff values for MCS according to some embodiments of the present disclosure.

Fig. 5B illustrates a schematic diagram of a service application running on a near RT RIC providing a selected backoff value to an E2 node in accordance with some embodiments of the present disclosure.

Fig. 6A illustrates a schematic diagram of training multiple AI or ML models corresponding to different channel estimation algorithms, according to some embodiments of the present disclosure.

Fig. 6B illustrates a schematic diagram of a service application running on a near RT RIC providing a selected channel estimation algorithm to an E2 node, according to some embodiments of the present disclosure.

Fig. 7 illustrates a schematic diagram of a network in accordance with various embodiments of the present disclosure.

Fig. 8 illustrates a schematic diagram of a wireless network in accordance with various embodiments of the present disclosure.

Fig. 9 illustrates a block diagram of components capable of reading instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) and performing any one or more of the methods discussed herein, according to some example embodiments of the present disclosure.

Detailed Description

Various aspects of the illustrative embodiments will be described using terms commonly employed by those skilled in the art to convey the substance of the disclosure to others skilled in the art. However, it will be apparent to those skilled in the art that many alternative embodiments may be implemented using portions of the described aspects. For purposes of explanation, specific numbers, materials, and configurations are set forth in order to provide a thorough understanding of the illustrative embodiments. It will be apparent, however, to one skilled in the art that alternative embodiments may be practiced without these specific details. In other instances, well-known features may be omitted or simplified in order not to obscure the illustrative embodiments.

Furthermore, various operations will be described as multiple discrete operations in turn, in a manner that is most helpful in understanding the illustrative embodiments; however, the order of description should not be construed as to imply that these operations are necessarily order dependent. In particular, these operations need not be performed in the order of presentation.

The phrases "in an embodiment," "in one embodiment," and "in some embodiments" are repeated herein. These phrases generally do not refer to the same embodiment; however, they may also refer to the same embodiments. The terms "comprising," "having," and "including" are synonymous, unless the context dictates otherwise. The phrases "A or B" and "A/B" mean "(A), (B), or (A and B)".

An open radio access network (O-RAN) architecture includes a Radio Unit (RU), a Distributed Unit (DU), a Centralized Unit (CU), and a Radio Access Network (RAN) intelligent controller (RIC), where the RIC may be configured to support non-real-time (RT) or near RT configuration or optimization of Medium Access Control (MAC) or L1 functions residing in the DU, and the RU, DU, and CU may be collectively referred to as E2 nodes. The non-RT or near RT RIC control loop runs slower than the periods typically used for MAC or L1 functions (running on a time slot or faster timescale).

In general, the radio performance of various algorithms employed in the MAC or L1 functions depends on factors such as channel conditions, interference conditions, traffic load, etc. It is possible and advantageous to utilize Artificial Intelligence (AI) or Machine Learning (ML) in RIC to optimize algorithm selection in DUs. However, in the O-RAN architecture, no mechanism of algorithm selection in RIC control DUs is currently defined.

One particular important area relates to beamforming or massive multiple input multiple output (mimo), a key feature used by 5G wireless communication systems to enhance communication range, throughput, and capacity. The beamforming algorithm may be optimized according to local conditions in the cell (e.g., local propagation, traffic, and interference conditions). The O-RAN architecture is providing support for AI-or ML-based mimo or beamforming optimization, where service applications located in non-RT or near-RT RIC can adjust beamforming related parameters, but so far this takes into account so-called "grid of beams" (GoB) -based beamforming algorithms, where a set of candidate beams is defined at each cell, user Equipments (UEs) are assigned to the beams, and beam acquisition or tracking or failure procedures are defined for the management of the beams.

However, non-GoB-based beamforming algorithms are also implemented for 5G wireless communication systems, especially for lower sub-6 GHz frequency bands, such as Sounding Reference Symbol (SRS) -based beamforming algorithms that rely on uplink and downlink correspondence, where the uplink and downlink beams are calculated "on the fly" based on channel measurements made using SRS, rather than being selected from a set of predefined beams. In the O-RAN architecture, there is no AI or ML assisted enhancement for non-GoB-based beamforming algorithms. SRS-based beamforming algorithms are particularly attractive for mimo arrays because very accurate channel state information can be obtained on the next generation base station (gNB) with very little overhead in the Downlink (DL) or Uplink (UL) channels.

It should be noted that the wireless performance of non-GoB-based beamforming algorithms (e.g., SRS-based beamforming algorithms) depends largely on channel conditions and periodicity of SRS measurements. In case of radio performance degradation of the non-GoB-based beamforming algorithm, the MAC scheduler in the DU may need to take this into account when allocating the Modulation Coding Scheme (MCS) in order to avoid excessive block error rate or hybrid automatic repeat request (HARQ) transmission delay. Alternatively, it may be desirable to adjust the beamforming algorithm itself to use a more robust configuration, e.g., to base the beamforming algorithm on a long-term average of the channel conditions rather than on an instantaneous (but outdated) channel estimate. Another possibility is that if the wireless performance of a non-GoB-based beamforming algorithm is predicted to be poor, an alternative algorithm may be used.

In view of the above, a mechanism is proposed by which the RIC controls the use of communication-related operations and/or communication-related algorithms in the E2 node. For example, providing a non-RT RIC with multiple sets of training data for AI or ML models, each set of training data corresponding to a particular communication-related algorithm option in a DU; each set of training data includes RAN measurements (e.g., reference Signal Received Power (RSRP) and signal to interference and noise ratio (SINR) measurements) and non-RAN-enhanced data (e.g., location and mobility related information); also included in each set of training data are performance metrics such as realized throughput; AI or ML models are trained to predict performance metrics based on RAN measurements and location and mobility related information; the AI or ML model is trained and then provided to service applications running on non-RT or near RT RICs; and service applications running on non-RT or near RT RIC will: a) A policy to be transmitted to the DU is formulated and then the DU uses the policy to determine a communication-related algorithm with the best performance metric, or b) a communication-related algorithm with the best performance metric is predicted based on each UE option and selected and then transmitted to the DU. An application service running on a non-RT or near RT RIC will then signal the policy or communication related algorithm with the best performance metric to the DU via the E2 interface, which will apply the policy or communication related algorithm with the best performance metric.

FIG. 1 illustrates a flow chart of a method 100 for use in a RIC according to some embodiments of the present disclosure. As shown in fig. 1, the method 100 includes: s102, determining policy guidance, algorithm selection or model recommendation based on RAN measurement results and location or mobility related information associated with the UE; and S104, providing policy guidance, algorithm selection or model recommendation to the E2 node for use when the RAN communicates with the UE, wherein the policy guidance is used for indicating a policy for determining communication related operations, the algorithm selection is used for indicating a communication related algorithm, and the model recommendation is used for indicating one of a plurality of AI or ML models for offline training to realize the communication related algorithm.

In some embodiments, the policy directive may be determined using an AI or ML model deployed in a service application running on the RIC, the AI or ML model configured to estimate performance metrics for respective communication-related operations based on RAN measurements and location or mobility-related information associated with the UE and to output the policy directive, and the communication-related operations determined based on the policy indicated by the policy directive have the best performance metrics. The RIC may be a near RT RIC and the AI or ML model may be trained in a near RT RIC or a non-RT RIC. The AI or ML model may be trained based on RAN measurements and location or mobility related information associated with the plurality of UEs and performance metrics of respective communication related operations implemented by the plurality of UEs.

In some embodiments, the algorithm selection may be determined using a plurality of AI or ML models deployed in a service application running on the RIC, the AI or ML models being associated with a respective plurality of communication-related algorithms, each of the plurality of AI or ML models being configured to output a performance metric for the respective communication-related algorithm based on RAN measurements and location or mobility-related information associated with the UE, and the communication-related algorithm indicated by the algorithm selection having the best performance metric. The RIC may be a near RT RIC and the multiple AI or ML models may be trained in non-RT RIC or non-RT RIC. The multiple AI or ML models may be trained based on RAN measurements and location or mobility related information associated with the multiple UEs and performance metrics of respective communication related algorithms implemented by the multiple UEs.

In some embodiments, multiple offline trained AI or ML models may be trained based on RAN measurements and location or mobility related information associated with multiple UEs and results of respective communication related algorithms implemented by the multiple UEs.

In some embodiments, the RAN measurements associated with the UE include channel quality metrics, e.g., RSRP measurements or SINR measurements, on the uplink or downlink associated with the UE.

In some embodiments, the algorithm selection is used to indicate a channel estimation algorithm or a beamforming algorithm. Alternatively, the algorithm selects a backoff value or resource management plan for indicating the MCS.

Five specific embodiments are described herein, of which embodiments 1, 2, 3 are more general embodiments and enable the near RT RIC to control the E2 node, embodiments 4 and 5 are more specific examples based on embodiments 1-3.

Note that mobility related information may include speed and direction of travel, but may also be a more contextual measure, e.g. it may include an identification of the road and speed and direction of travel along the road, and the AI or ML model may learn that under certain conditions, UEs traveling along the road may benefit from a particular beamforming configuration at a particular location.

Example 1: policy guidance

In this embodiment, an AI or ML model for providing policy guidance is deployed in a service application running on a near RT RIC, and may estimate performance metrics for individual communication-related operations based on RAN measurements and location or mobility-related information associated with the UE and output policy guidance indicating policies for determining communication-related operations (e.g., MCS backoff, instantaneous or average channel estimation, beamforming, or a combination thereof). For example, such a policy may be given: if the measured SINR < X, Y is performed. Based on the policy guidelines and the real-time RAN measurements, the E2 node determines a corresponding communication-related operation. Fig. 2 illustrates a schematic diagram of a service application running on a near RT RIC providing policy guidelines to an E2 node, according to some embodiments of the disclosure.

Example 2: off-line trained AI or ML model selection

The AI or ML model deploying offline training in the E2 node is a viable solution to implement data driven algorithms (e.g., beamforming, channel estimation, symbol detection, decoding, etc.). One key challenge of offline trained AI or ML models is the so-called model mismatch, i.e. offline trained AI or ML models are trained under the assumption that they are not valid during model reasoning. A simple and effective solution to overcome model mismatch is to train multiple AI or ML models under different assumptions and select the most appropriate training model for reasoning. In this embodiment, the service application running on the near RT RIC is configured to select the appropriate offline trained AI or ML model. The output of the service application running on the near RT RIC is a model recommendation for the AI or ML model trained offline. The output of the service application running on the near RT RIC is provided by the near RT RIC to the E2 node over the E2 interface. The service application running on the near RT RIC may be implemented by another trained AI or ML model or based on a "classical" signal processing algorithm.

To illustrate embodiment 2, consider a channel estimation algorithm that utilizes an AI or ML model that is trained offline. It is assumed that multiple offline trained AI or ML models are trained offline for different channel models (e.g., urban macro-cells, urban micro-cells, indoor, etc.) or are trained offline using measurement data from different deployment scenarios. Inputs to a service application running on the near RT RIC may include RSRP measurements associated with the UE, SINR measurements, and non-RAN-enhanced data (e.g., location/mobility related information). The output of a service application running on a near RT RIC is a model recommendation indicating an AI or ML model trained offline or a relevant parameter to be considered by the channel estimation algorithm. Fig. 3 illustrates a schematic diagram of a service application running on a near RT RIC providing model recommendations to an E2 node, according to some embodiments of the present disclosure.

Example 3: beamforming algorithm selection

In this embodiment, multiple AI or ML models corresponding to different beamforming algorithms are deployed in a service application running on a near RT RIC, and the performance metrics of the different beamforming algorithms can be estimated and the beamforming algorithm with the best performance metrics reported to the E2 node. Fig. 4A illustrates a schematic diagram of training multiple AI or ML models corresponding to different beamforming algorithms according to some embodiments of the present disclosure. Fig. 4B illustrates a schematic diagram of a service application running on a near RT RIC providing a selected beamforming algorithm to an E2 node according to some embodiments of the present disclosure. Example beamforming algorithms include PMI-based (depending on feedback from the UE), beam grid-based, compressed measurement result-based, or SRS-based beamforming algorithms. The selected beamforming algorithm is provided by the near RT RIC to the E2 node over the E2 interface.

Example 4: beam forming performance prediction

In the present embodiment, a plurality of AI or ML models corresponding to different backoff values for a specific MCS are deployed in an application service running on a near RT-RIC, and it is possible to estimate the throughput for the implementation of the different backoff values for the MCS and report the backoff value with the best throughput to the E2 node. Inputs to a service application running on a near RT RIC (i.e., inputs to multiple AI or ML models corresponding to different backoff values for MCS) include RSRP measurements, SINR measurements, and non-RAN enhancement data (e.g., location or mobility related information). The RSRP measurement and SINR measurement may include DL RSRP and SINR measurement and/or UL RSRP and SINR measurement.

Fig. 5A illustrates a schematic diagram of training multiple AI or ML models corresponding to different backoff values for MCS according to some embodiments of the present disclosure. Fig. 5B illustrates a schematic diagram of a service application running on a near RT RIC providing a selected backoff value to an E2 node in accordance with some embodiments of the present disclosure. For each UE, a service application running on the near RT RIC runs inferences of multiple AI or ML models corresponding to different backoff values for the MCS to estimate the throughput achieved for the multiple backoff values and selects the backoff value with the best throughput. Alternatively, a service application running on a near RT RIC may directly infer the backoff value with the best throughput without first estimating the throughput achieved for the different backoff values. The selected backoff value is then provided by the near RT RIC to the E2 node over the E2 interface.

Example 5: channel estimation selection

In this embodiment, multiple AI or ML models corresponding to different channel estimation algorithms are deployed in an application service running on a near RT RIC, and the performance metrics of the different channel estimation algorithms can be estimated and the channel estimation algorithm with the best performance metrics reported to the E2 node to configure the beamforming algorithm. Inputs to multiple AI or ML models corresponding to different channel estimation algorithms (i.e., inputs to an application service running on a near RT RIC) include RSRP measurements, SINR measurements, and non-RAN-enhanced data (e.g., location or mobility related information). The RSRP measurement and SINR measurement may include DL RSRP and SINR measurement and/or UL RSRP and SINR measurement.

Fig. 6A illustrates a schematic diagram of training multiple AI or ML models corresponding to different channel estimation algorithms, according to some embodiments of the present disclosure. Fig. 6B illustrates a schematic diagram of a service application running on a near RT RIC providing a selected channel estimation algorithm to an E2 node, according to some embodiments of the present disclosure. Examples of performance metrics include, but are not limited to, throughput, delay, coverage, or any function of these or other performance metrics. For each UE, a service application running on the near RT RIC runs inferences of multiple AI or ML models corresponding to different channel estimation algorithms to estimate performance metrics for the different channel estimation algorithms and selects the channel estimation algorithm with the best performance metric. The selected channel estimation algorithm is then provided by the near RT RIC to the E2 node over the E2 interface.

7-8 illustrate various systems, devices, and components that may implement aspects of the disclosed embodiments.

Fig. 7 illustrates a schematic diagram of a network 700, according to various embodiments of the disclosure. The network 700 may operate in accordance with 3GPP technical specifications for Long Term Evolution (LTE) or 5G/NR systems. However, the example embodiments are not limited in this respect and the described embodiments may be applied to other networks that benefit from the principles described herein, such as future 3GPP systems, and the like.

Network 700 may include a UE 702, which may include any mobile or non-mobile computing device designed to communicate with a Radio Access Network (RAN) 704 via an over-the-air connection. The UE 702 may be, but is not limited to, a smart phone, tablet computer, wearable computer device, desktop computer, laptop computer, in-vehicle infotainment device, in-vehicle entertainment device, dashboard, heads-up display device, in-vehicle diagnostic device, dashboard mobile device, mobile data terminal, electronic engine management system, electronic/engine control unit, electronic/engine control module, embedded system, sensor, microcontroller, control module, engine management system, network device, machine-to-machine (M2M) or device-to-device (D2D) device, internet of things (IoT) device, etc.

In some embodiments, the network 700 may include multiple UEs directly coupled to each other through a side link interface. The UE may be an M2M/D2D device that communicates using a physical sidelink channel (e.g., without limitation, a Physical Sidelink Broadcast Channel (PSBCH), a Physical Sidelink Discovery Channel (PSDCH), a Physical Sidelink Shared Channel (PSSCH), a Physical Sidelink Control Channel (PSCCH), a physical sidelink substrate channel (PSFCH), etc.).

In some embodiments, the UE 702 may also communicate with an Access Point (AP) 706 over an over-the-air connection. AP 706 may manage Wireless Local Area Network (WLAN) connections that may be used to offload some/all network traffic from RAN 704. The connection between the UE 702 and the AP 706 may be consistent with any IEEE 802.11 protocol, where the AP 706 may be wireless fidelityAnd a router. In some embodiments, the UE 702, RAN 704, and AP 706 may utilize cellular WLAN aggregation (e.g., LTE-WLAN aggregation (LWA)/lightweight IP (LWIP)). Cellular WLAN aggregation may involve configuring the UE 702 by the RAN 704 to utilize both cellular radio resources and WLAN resources.

RAN 704 may include one or more access nodes, e.g., AN Access Node (AN) 708. The AN 708 may terminate the air interface protocol of the UE 702 by providing access layer protocols including Radio Resource Control (RRC) protocol, packet Data Convergence Protocol (PDCP), radio Link Control (RLC) protocol, medium Access Control (MAC) protocol, and L1 protocol. In this way, the AN 708 may enable a data/voice connection between the Core Network (CN) 720 and the UE 702. In some embodiments, AN 708 may be implemented in a discrete device or as one or more software entities running on a server computer (as part of a virtual network, which may be referred to as a distributed RAN (CRAN) or virtual baseband unit pool, for example). The AN 708 may be referred to as a Base Station (BS), a next generation base station (gNB), a RAN node, AN evolved node B (eNB), a next generation eNB (ng eNB), a node B (NodeB), a roadside unit (RSU), a transmission reception point (TRxP), a transmission point (TRP), and the like. The AN 708 may be a macrocell base station or a low power base station for providing a microcell, picocell, or other similar cell with a smaller coverage area, smaller user capacity, or higher bandwidth than the macrocell.

In embodiments where the RAN 704 includes multiple ANs, they may be coupled to each other through AN X2 interface (if the RAN 704 is AN LTE RAN) or AN Xn interface (if the RAN 704 is a 5G RAN). In some embodiments, the X2/Xn interface, which may be separated into control/user plane interfaces, may allow the AN to communicate information related to handoff, data/context transfer, mobility, load management, interference coordination, etc.

The AN of the RAN 704 may respectively manage one or more cells, groups of cells, component carriers, etc. to provide AN air interface for network access to the UE 702. The UE 702 may be connected simultaneously with multiple cells provided by the same or different ANs of the RAN 704. For example, the UE 702 and the RAN 704 may use carrier aggregation to allow the UE 702 to connect with multiple component carriers, each component carrier corresponding to a primary cell (PCell) or a secondary cell (SCell). In a dual connectivity scenario, the first AN may be a primary network node providing a primary cell group (MCG) and the second AN may be a secondary network node providing a Secondary Cell Group (SCG). The first/second AN may be any combination of eNB, gNB, ng-enbs, etc.

RAN 704 may provide the air interface on licensed spectrum or unlicensed spectrum. To operate in unlicensed spectrum, a node may use License Assisted Access (LAA), enhanced LAA (eLAA), and/or further enhanced LAA (feLAA) mechanisms based on Carrier Aggregation (CA) techniques of PCell/Scell. Prior to accessing the unlicensed spectrum, the node may perform a medium/carrier sensing operation based on, for example, a Listen Before Talk (LBT) protocol.

In a vehicle-to-everything (V2X) scenario, the UE 702 or AN 708 may be or act as a roadside unit (RSU), which may refer to any transport infrastructure entity for V2X communications. The RSU may be implemented in or by a suitable AN or stationary (or relatively stationary) UE. An RSU implemented in or by a UE may be referred to as a "UE-type RSU"; an RSU implemented in or by an eNB may be referred to as an "eNB-type RSU"; RSUs implemented in or by next generation nodebs (gnbs) may be referred to as "gNB-type RSUs" or the like. In one example, the RSU is a computing device coupled with a radio frequency circuit located at the roadside that provides connectivity support to passing vehicle UEs. The RSU may also include internal data storage circuitry for storing intersection map geometry, traffic statistics, media, and applications/software for sensing and controlling ongoing vehicle and pedestrian traffic. The RSU may provide very low latency communications required for high speed events (e.g., collision avoidance, traffic alerts, etc.). Additionally or alternatively, the RSU may provide other cellular/WLAN communication services. The components of the RSU may be enclosed in a weather-proof enclosure suitable for outdoor installation, and may include a network interface controller to provide a wired connection (e.g., ethernet) to a traffic signal controller or backhaul network.

In some embodiments, the RAN 704 may be an LTE RAN 710 including an evolved node B (eNB), e.g., eNB 712. The LTE RAN 710 may provide an LTE air interface with the following features: subcarrier spacing (SCS) of 15 kHz; a single carrier frequency division multiple access (SC-FDMA) waveform for the Uplink (UL) and a cyclic prefix orthogonal frequency division multiplexing (CP-OFDM) waveform for the Downlink (DL); turbo code for data, TBCC for control, etc. The LTE air interface may rely on channel state information reference signals (CSI-RS) for CSI acquisition and beam management; PDSCH/PDCCH demodulation is performed in dependence on Physical Downlink Shared Channel (PDSCH)/Physical Downlink Control Channel (PDCCH) demodulation reference signals (DMRS); and relying on Cell Reference Signals (CRS) for cell search and initial acquisition, channel quality measurements, and channel estimation, and on channel estimation for coherent demodulation/detection at the UE. The LTE air interface may operate on the 6GHz sub-band.

In some embodiments, RAN 704 may be a Next Generation (NG) -RAN 714 with a gNB (e.g., gNB 716) or gn-eNB (e.g., NG-eNB 718). The gNB 716 may connect with 5G enabled UEs using a 5G NR interface. The gNB 716 may connect with the 5G core through a NG interface, which may include an N2 interface or an N3 interface. The NG-eNB 718 may also connect with the 5G core over the NG interface, but may connect with the UE over the LTE air interface. The gNB 716 and the ng-eNB 718 may be connected to each other through an Xn interface.

In some embodiments, the NG interface may be divided into two parts, an NG user plane (NG-U) interface that carries traffic data between the UPF 748 and the node of the NG-RAN 714 (e.g., an N3 interface) and an NG control plane (NG-C) interface that is a signaling interface between the access and mobility management function (AMF) 744 and the node of the NG-RAN 714 (e.g., an N2 interface).

NG-RAN 714 may provide a 5G-NR air interface with the following features: variable subcarrier spacing (SCS); cyclic prefix-orthogonal frequency division multiplexing (CP-OFDM) for Downlink (DL), CP-OFDM for UL, and DFT-s-OFDM; polarity, repetition, simplex, and reed-muller codes for control; and a low density parity check code (LDPC) for data. The 5G-NR air interface may rely on channel state reference signals (CSI-RS), PDSCH/PDCCH demodulation reference signals (DMRS) like the LTE air interface. The 5G-NR air interface may not use Cell Reference Signals (CRSs), but may use Physical Broadcast Channel (PBCH) demodulation reference signals (DMRS) for PBCH demodulation; phase tracking of PDSCH using Phase Tracking Reference Signals (PTRS); and performing time tracking using the tracking reference signal. The 5G-NR air interface may operate on an FR1 band including a 6GHz sub-band or an FR2 band including 24.25GHz to 52.6GHz bands. The 5G-NR air interface may include a synchronization signal and a PBCH block (SSB), which is a region of a downlink resource grid including a Primary Synchronization Signal (PSS)/Secondary Synchronization Signal (SSS)/PBCH.

In some embodiments, the 5G-NR air interface may use bandwidth part (BWP) for various purposes. For example, BWP may be used for dynamic adaptation of SCS. For example, the UE 702 may be configured with multiple BWP, where each BWP configuration has a different SCS. When a BWP change is indicated to the UE 702, the SCS of the transmission is also changed. Another use case of BWP relates to power saving. In particular, the UE 702 may be configured with multiple BWPs having different numbers of frequency resources (e.g., PRBs) to support data transmission in different traffic load scenarios. BWP containing a smaller number of PRBs may be used for data transmission with smaller traffic load while allowing power saving at the UE 702 and in some cases the gNB 716. BWP comprising a large number of PRBs may be used for scenarios with higher traffic load.

The RAN 704 is communicatively coupled to a CN 720 that includes network elements to provide various functions to support data and telecommunications services to clients/subscribers (e.g., users of the UE 702). The components of CN 720 may be implemented in one physical node or in a different physical node. In some embodiments, network Function Virtualization (NFV) may be used to virtualize any or all of the functions provided by the network elements of CN 720 onto physical computing/storage resources in servers, switches, and the like. The logical instance of the CN 720 may be referred to as a network slice, and the logical instance of a portion of the CN 720 may be referred to as a network sub-slice.

In some embodiments, CN 720 may be LTE CN 722, which may also be referred to as EPC. LTE CN 722 may include a Mobility Management Entity (MME) 724, a Serving Gateway (SGW) 726, a serving General Packet Radio Service (GPRS) support node (SGSN) 728, a Home Subscriber Server (HSS) 730, a Proxy Gateway (PGW) 732, and a policy control and charging rules function (PCRF) 734, which are coupled to each other via an interface (or "reference point") as shown. The function of the elements of LTE CN 722 may be briefly described as follows.

MME 724 may implement mobility management functions to track the current location of UE 702 to facilitate paging, bearer activation/deactivation, handover, gateway selection, authentication, etc.

SGW 726 may terminate the S1 interface towards the RAN and route data packets between the RAN and LTE CN 722. SGW 726 may be a local mobility anchor for inter-RAN node handover and may also provide an anchor for inter-3 GPP mobility. Other responsibilities may include lawful interception, billing, and some policy enforcement.

SGSN 728 can track the location of UE 702 and perform security functions and access control. In addition, SGSN 728 may perform EPC inter-node signaling for mobility between different RAT networks; MME 724 specified PDN and S-GW selection; MME selection for handover, etc. The S3 reference point between MME 724 and SGSN 728 may enable user and bearer information exchange for inter-3 GPP network mobility in the idle/active state.

HSS 730 may include a database for network users that includes subscription-related information that supports network entity handling communication sessions. HSS 730 may provide support for routing/roaming, authentication, authorization, naming/addressing resolution, location dependencies, and the like. The S6a reference point between HSS 730 and MME 724 may enable the transmission of subscription and authentication data for authenticating/authorizing user access to LTE CN 720.

PGW 732 may terminate an SGi interface towards a Data Network (DN) 736 that may include an application/content server 738. PGW 732 may route data packets between LTE CN 722 and data network 736. PGW 732 may be coupled with SGW 726 via an S5 reference point to facilitate user plane tunneling and tunnel management. PGW 732 may also include nodes (e.g., PCEFs) for policy enforcement and charging data collection. In addition, the SGi reference point between PGW 732 and data network 736 may be, for example, an operator external public, private PDN, or an operator internal packet data network for providing IP Multimedia Subsystem (IMS) services. PGW 732 may be coupled with PCRF 734 via a Gx reference point.

PCRF 734 is a policy and charging control element of LTE CN 722. PCRF 734 may be communicatively coupled to application/content server 738 to determine appropriate quality of service (QoS) and charging parameters for the service flows. PCRF 732 may provide the relevant rules to the PCEF (via the Gx reference point) with the appropriate Traffic Flow Templates (TFTs) and QoS Class Identifiers (QCIs).

In some embodiments, CN 720 may be a 5G core network (5 GC) 740. The 5gc 740 may include an authentication server function (AUSF) 742, an access and mobility management function (AMF) 744, a Session Management Function (SMF) 746, a User Plane Function (UPF) 748, a Network Slice Selection Function (NSSF) 750, a network open function (NEF) 752, an NF storage function (NRF) 754, a Policy Control Function (PCF) 756, a Unified Data Management (UDM) 758, and an Application Function (AF) 760, coupled to each other through an interface (or "reference point") as shown. The function of the elements of the 5gc 740 may be briefly described as follows.

AUSF 742 may store data for authentication of UE 702 and process authentication related functions. AUSF 742 may facilitate a common authentication framework for various access types. In addition to communicating with other elements of the 5gc 740 through reference points as shown, the AUSF 742 may also present an interface based on the Nausf service.

The AMF 744 may allow other functions of the 5gc 740 to communicate with the UE 702 and RAN 704 and subscribe to notifications about mobility events of the UE 702. The AMF 744 may be responsible for registration management (e.g., registering the UE 702), connection management, reachability management, mobility management, lawful intercept AMF related events, and access authentication and authorization. The AMF 744 may provide for the transmission of Session Management (SM) messages between the UE 702 and the SMF 746, and acts as a transparent proxy for routing SM messages. The AMF 744 may also provide for transmission of SMS messages between the UE 702 and the SMSF. The AMF 744 may interact with the AUSF 742 and the UE 702 to perform various security anchoring and context management functions. Furthermore, the AMF 744 may be an end point of the RAN CP interface, which may include or be an N2 reference point between the RAN 704 and the AMF 744; the AMF 744 may serve as an endpoint for NAS (N1) signaling and perform NAS ciphering and integrity protection. The AMF 744 may also support NAS signaling with the UE 702 over the N3 IWF interface.

The SMF 746 may be responsible for SM (e.g., tunnel management, session establishment between UPF 748 and AN 708); UE IP address allocation and management (including optional authorization); selection and control of the UP function; configuring flow control at UPF 748 to route traffic to an appropriate destination; termination of the interface to the policy control function; control policy enforcement, charging, and a portion of QoS; legal interception (for SM events and interfaces to LI systems); terminating the SM portion of the NAS message; downlink data notification; AN-specific SM information is initiated (sent over N2 to AN 708 via AMF 744); and determining the SSC mode of the session. SM may refer to the management of PDU sessions, and PDU session or "session" may refer to a PDU connection service that provides or enables PDU exchanges between UE 702 and data network 736.

UPF 748 may serve as an anchor point for intra-RAT and inter-RAT mobility, an external PDU session point interconnected with data network 736, and a branching point to support multi-homing PDU sessions. UPF 748 may also perform packet routing and forwarding, perform packet inspection, perform policy rules user plane part, lawful interception packets (UP collection), perform traffic usage reporting, perform QoS processing for the user plane (e.g., packet filtering, gating, UL/DL rate enforcement), perform uplink traffic verification (e.g., SDF to QoS flow mapping), transport layer packet tagging in the uplink and downlink, and perform downlink packet buffering and downlink data notification triggering. UPF 748 may include an uplink classifier to support routing traffic flows to a data network.

NSSF 750 may select a set of network slice instances to serve UE 702. NSSF 750 may also determine the allowed Network Slice Selection Assistance Information (NSSAI) and the mapping to subscribed individual NSSAIs (S-NSSAIs), if desired. NSSF 750 may also determine the set of AMFs to use for serving UE 702, or a list of candidate AMFs, based on a suitable configuration and possibly by querying NRF 754. The selection of a set of network slice instances of UE 702 may be triggered by AMF 744 (with which UE 702 registers by interacting with NSSF 750), which may result in a change in AMF. NSSF 750 may interact with AMF 744 via an N22 reference point; and may communicate with another NSSF in the visited network via an N31 reference point (not shown). In addition, NSSF 750 may expose an interface based on the Nnssf service.

The NEF 752 may securely disclose services and capabilities provided by 3GPP network functions for third parties, internal exposure/re-exposure, AF (e.g., AF 760), edge computing or fog computing systems, and the like. In these embodiments, the NEF 752 may authenticate, authorize, or restrict AF. The NEF 752 may also convert information exchanged with the AF 760 and information exchanged with internal network functions. For example, the NEF 752 may translate between an AF service identifier and internal 5GC information. The NEF 752 may also receive information from other NFs based on their public capabilities. This information may be stored as structured data at the NEF 752 or at the data store NF using a standardized interface. The NEF 752 may then re-expose the stored information to other NFs and AFs, or for other purposes such as analysis. In addition, NEF 752 may expose an interface based on Nnef services.

The NRF 754 may support a service discovery function, receive NF discovery requests from NF instances, and provide information of the discovered NF instances to the NF instances. NRF 754 also maintains information of available NF instances and services supported by them. As used herein, the terms "instantiate," "instance," and the like may refer to creating an instance, "instance" may refer to a specific occurrence of an object, which may occur, for example, during execution of program code. In addition, NRF 754 may expose an interface based on Nnrf services.

PCF 756 may provide policy rules to control plane functions to enforce those policy rules and may also support a unified policy framework to manage network behavior. PCF 756 may also implement a front end to access subscription information related to policy decisions in the UDR of UDM 758. In addition to communicating with functions through reference points as shown, PCF 756 also presents an interface based on the Npcf service.

The UDM 758 may process subscription related information to support network entities in handling communication sessions and may store subscription data for the UE 702. For example, subscription data may be transmitted via an N8 reference point between UDM 758 and AMF 744. UDM 758 may include two parts: application front-end and User Data Record (UDR). The UDR may store policy data and subscription data for UDM 758 and PCF 756, and/or structured data and application data for NEF 752 for exposure (including PFD for application detection, application request information for multiple UEs 702). The UDR may expose an interface based on Nudr services to allow the UDM 758, PCF 756, and NEF 752 to access specific sets of stored data, as well as to read, update (e.g., add, modify), delete, and subscribe to notifications of related data changes in the UDR. The UDM may include a UDM-FE (UDM front end) that is responsible for handling credentials, location management, subscription management, etc. Several different front ends may serve the same user in different transactions. The UDM-FE accesses subscription information stored in the UDR and performs authentication credential processing, user identification processing, access authorization, registration/mobility management, and subscription management. In addition to communicating with other NFs through reference points as shown, the UDM 758 may also expose Nudm service based interfaces.

AF 760 may provide application impact on traffic routing, provide access to the NEF, and interact with the policy framework for policy control.

In some embodiments, the 5gc 740 may enable edge computation by selecting an operator/third party service that is geographically close to the point where the UE 702 connects to the network. This may reduce delay and load on the network. To provide edge computing implementations, the 5gc 740 may select the UPF 748 near the UE 702 and perform traffic steering from the UPF 748 to the data network 736 over the N6 interface. This may be based on the UE subscription data, UE location, and information provided by AF 760. Thus, AF 760 may affect UPF (re) selection and traffic routing. Based on the carrier deployment, the network operator may allow the AF 760 to interact directly with the associated NF when the AF 760 is considered a trusted entity. In addition, AF 760 may present an interface based on Naf services.

Data network 736 may represent various network operator services, internet access, or third party services that may be provided by one or more servers, including, for example, application/content server 738.

Fig. 8 schematically illustrates a wireless network 800 according to various embodiments. The wireless network 800 may include a UE 802 in wireless communication with AN 804. The UE 802 and the AN 804 may be similar to and substantially interchangeable with the synonym components described elsewhere herein.

The UE 802 may be communicatively coupled with the AN 804 via a connection 806. Connection 806 is shown as an air interface to enable communicative coupling, and may operate at millimeter wave or below 6GHz frequencies in accordance with a cellular communication protocol, such as the LTE protocol or the 5G NR protocol.

UE 802 may include a host platform 808 coupled to a modem platform 810. Host platform 808 can include application processing circuitry 812, which can be coupled with protocol processing circuitry 814 of modem platform 810. The application processing circuitry 812 may run various applications for the UE 802 that acquire/receive its application data. The application processing circuitry 812 may also implement one or more layer operations to transmit/receive application data to/from the data network. These layer operations may include transport (e.g., UDP) and internet (e.g., IP) operations.

Protocol processing circuitry 814 may implement one or more layers of operations to facilitate transmission or reception of data over connection 806. Layer operations implemented by the protocol processing circuit 814 may include, for example, medium Access Control (MAC), radio Link Control (RLC), packet Data Convergence Protocol (PDCP), radio Resource Control (RRC), and non-access stratum (NAS) operations.

Modem platform 810 may further include digital baseband circuitry 816, which digital baseband circuitry 816 may implement one or more layer operations "below" the layer operations performed by protocol processing circuitry 814 in the network protocol stack. These operations may include, for example, PHY operations including one or more of HARQ-ACK functions, scrambling/descrambling, encoding/decoding, layer mapping/demapping, modulation symbol mapping, received symbol/bit metric determination, multi-antenna port precoding/decoding, where these functions may include one or more of space-time, space-frequency, or spatial coding, reference signal generation/detection, preamble sequence generation and/or decoding, synchronization sequence generation/detection, control channel signal blind decoding, and other related functions.

Modem platform 810 may further include transmit circuitry 818, receive circuitry 820, RF circuitry 822, and RF front end (RFFE) circuitry 824, which may include or be connected to one or more antenna panels 826. Briefly, transmit circuitry 818 may include digital-to-analog converters, mixers, intermediate Frequency (IF) components, and the like; the receive circuitry 820 may include analog-to-digital converters, mixers, IF components, etc.; the RF circuitry 822 may include low noise amplifiers, power tracking components, and the like; RFFE circuit 824 may include filters (e.g., surface/bulk acoustic wave filters), switches, antenna tuners, beam forming components (e.g., phased array antenna components), and so forth. The selection and arrangement of the components of transmit circuitry 818, receive circuitry 820, RF circuitry 822, RFFE circuitry 824, and antenna panel 826 (collectively, "transmit/receive components") may be specific to the specifics of a particular implementation, e.g., whether the communication is Time Division Multiplexed (TDM) or Frequency Division Multiplexed (FDM), at mmWave or below 6GHz frequencies, etc. In some embodiments, the transmit/receive components may be arranged in a plurality of parallel transmit/receive chains, and may be arranged in the same or different chips/modules, etc.

In some embodiments, protocol processing circuit 814 may include one or more instances of control circuitry (not shown) to provide control functions for the transmit/receive components.

UE reception may be established through and via antenna panel 826, RFFE circuitry 824, RF circuitry 822, receive circuitry 820, digital baseband circuitry 816, and protocol processing circuitry 814. In some embodiments, antenna panel 826 may receive transmissions from AN 804 by receiving beamformed signals received by multiple antennas/antenna elements of one or more antenna panels 826.

UE transmissions may be established via and through protocol processing circuitry 814, digital baseband circuitry 816, transmit circuitry 818, RF circuitry 822, RFFE circuitry 824, and antenna panel 826. In some embodiments, the transmit components of UE 802 may apply spatial filtering to data to be transmitted to form transmit beams that are transmitted by the antenna elements of antenna panel 826.

Similar to the UE 802, the AN 804 may include a host platform 828 coupled with a modem platform 830. Host platform 828 may include application processing circuitry 832 coupled with protocol processing circuitry 834 of modem platform 830. The modem platform may also include digital baseband circuitry 836, transmit circuitry 838, receive circuitry 840, RF circuitry 842, RFFE circuitry 844, and antenna panel 846. The components of the AN 804 may be similar to the like-named components of the UE 802 and may be substantially interchangeable with the like-named components of the UE 802. In addition to performing data transmission/reception as described above, the components of the AN 804 may also perform various logical functions including, for example, radio Network Controller (RNC) functions such as radio bearer management, uplink and downlink dynamic radio resource management, and data packet scheduling.

Fig. 9 is a block diagram illustrating components capable of reading instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) and performing any one or more of the methods discussed herein, according to some example embodiments. In particular, fig. 9 shows a schematic diagram of a hardware resource 900, the hardware resource 900 comprising one or more processors (or processor cores) 910, one or more memory/storage devices 920, and one or more communication resources 930, wherein each of these processors, memory/storage devices, and communication resources may be communicatively coupled via a bus 940 or other interface circuitry. For embodiments that utilize node virtualization, such as Network Function Virtualization (NFV), the hypervisor 902 may be executed to provide an execution environment for one or more network slices/sub-slices to utilize the hardware resources 900.

Processor 910 may include, for example, a processor 912 and a processor 914. The processor 910 may be, for example, a Central Processing Unit (CPU), a Reduced Instruction Set Computing (RISC) processor, a Complex Instruction Set Computing (CISC) processor, a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP) such as a baseband processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Radio Frequency Integrated Circuit (RFIC), another processor (including those discussed herein), or any suitable combination thereof.

Memory/storage 920 may include main memory, disk storage, or any suitable combination thereof. Memory/storage 920 may include, but is not limited to, any type of volatile, nonvolatile, or semi-volatile memory such as Dynamic Random Access Memory (DRAM), static Random Access Memory (SRAM), erasable Programmable Read Only Memory (EPROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory, solid state memory, and the like.

Communication resources 930 may include an interconnection or network interface controller, component, or other suitable device to communicate with one or more peripheral devices 904 or one or more databases 906 or other network elements via network 908. For example, the communication resources 930 may include wired communication components (e.g., for coupling via USB, ethernet, etc.), cellular communication components, near Field Communication (NFC) components, and so forth,(or->Low energy) component, < >>Components, and other communication components.

The instructions 950 may include software, programs, applications, applets, applications, or other executable code for causing at least any one of the processors 910 to perform any one or more of the methods discussed herein. The instructions 950 may reside, completely or partially, within at least one of the processor 910 (e.g., in a cache of a processor), the memory/storage 920, or any suitable combination thereof. Further, any portion of instructions 950 may be transferred from any combination of peripherals 904 or databases 906 to hardware resource 900. Accordingly, the memory of the processor 910, the memory/storage device 920, the peripheral devices 904, and the database 906 are examples of computer-readable and machine-readable media.

The following paragraphs describe examples of various embodiments.

Example 1 includes an apparatus for use in a Radio Access Network (RAN) intelligent controller (RIC), wherein the apparatus comprises a processor circuit configured to cause the RIC to: determining policy guidelines, algorithm selections, or model recommendations based on RAN measurements associated with User Equipment (UE) and location or mobility related information; and providing the policy guidance, the algorithm selection, or the model recommendation to an E2 node for use when the RAN communicates with the UE, wherein the policy guidance is for indicating a policy for determining communication-related operations, the algorithm selection is for indicating a communication-related algorithm, and the model recommendation is for indicating one of a plurality of offline trained Artificial Intelligence (AI) or Machine Learning (ML) models to implement the communication-related algorithm.

Example 2 includes the apparatus of example 1, wherein the policy directive is determined using an AI or ML model deployed in a service application running on the RIC, the AI or ML model configured to estimate performance metrics for respective communication-related operations based on RAN measurements and location or mobility-related information associated with the UE and to output the policy directive, and the communication-related operations determined based on the policy indicated by the policy directive have the best performance metrics.

Example 3 includes the apparatus of example 2, wherein the RIC is a near Real Time (RT) RIC and the AI or ML model is trained in the near RT RIC or a non-RT RIC.

Example 4 includes the apparatus of example 3, wherein the AI or ML model is trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and performance metrics of respective communication related operations implemented by the plurality of UEs.

Example 5 includes the apparatus of example 1, wherein the algorithm selection is determined using a plurality of AI or ML models deployed in a service application running on the RIC, the plurality of AI or ML models respectively associated with a plurality of communication-related algorithms, each of the plurality of AI or ML models configured to output performance metrics for the respective communication-related algorithm based on RAN measurements and location or mobility-related information associated with the UE, and the communication-related algorithm indicated by the algorithm selection has the best performance metrics.

Example 6 includes the apparatus of example 5, wherein the RIC is a near Real Time (RT) RIC and the plurality of AI or ML models are trained in the near RT RIC or non-RT RIC.

Example 7 includes the apparatus of example 5, wherein the plurality of AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and performance metrics of respective communication related algorithms implemented by the plurality of UEs.

Example 8 includes the apparatus of example 1, wherein the plurality of offline trained AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and results of respective communication related algorithms implemented by the plurality of UEs.

Example 9 includes the apparatus of example 1, wherein the RAN measurement results associated with the UE include channel quality metrics on an uplink or a downlink associated with the UE.

Example 10 includes the apparatus of example 9, wherein the channel quality metric comprises a Reference Signal Received Power (RSRP) measurement or a signal-to-interference-and-noise ratio (SINR) measurement.

Example 11 includes the apparatus of example 1, wherein the algorithm selection is to instruct a channel estimation algorithm or a beamforming algorithm.

Example 12 includes the apparatus of example 1, wherein the algorithm selects a backoff value to indicate a Modulation Coding Scheme (MCS).

Example 13 includes the apparatus of example 1, wherein the algorithm selection is to indicate a resource management plan.

Example 14 includes a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by processor circuitry of a Radio Access Network (RAN) intelligent controller (RIC), cause the RIC to: determining policy guidelines, algorithm selections, or model recommendations based on RAN measurements associated with User Equipment (UE) and location or mobility related information; and providing the policy guidance, the algorithm selection, or the model recommendation to an E2 node for use when the RAN communicates with the UE, wherein the policy guidance is for indicating a policy for determining communication-related operations, the algorithm selection is for indicating a communication-related algorithm, and the model recommendation is for indicating one of a plurality of offline trained Artificial Intelligence (AI) or Machine Learning (ML) models to implement the communication-related algorithm.

Example 15 includes the computer-readable storage medium of example 14, wherein the policy directive is determined using an AI or ML model deployed in a service application running on the RIC, the AI or ML model configured to estimate performance metrics for respective communication-related operations based on RAN measurements and location or mobility-related information associated with the UE and to output the policy directive, and the communication-related operations determined based on the policy indicated by the policy directive have the best performance metrics.

Example 16 includes the computer-readable storage medium of example 15, wherein the RIC is a near real-time (RT) RIC and the AI or ML model is trained in the near RT RIC or non-RT RIC.

Example 17 includes the computer-readable storage medium of example 16, wherein the AI or ML model is trained based on RAN measurements and location or mobility-related information associated with a plurality of UEs and performance metrics of respective communication-related operations implemented by the plurality of UEs.

Example 18 includes the computer-readable storage medium of example 14, wherein the algorithm selection is determined using a plurality of AI or ML models deployed in a service application running on the RIC, the plurality of AI or ML models respectively associated with a plurality of communication-related algorithms, each of the plurality of AI or ML models configured to output performance metrics of the respective communication-related algorithm based on RAN measurements and location or mobility-related information associated with the UE, and the communication-related algorithm indicated by the algorithm selection has the best performance metrics.

Example 19 includes the computer-readable storage medium of example 18, wherein the RIC is a near real-time (RT) RIC and the plurality of AI or ML models are trained in the near RT RIC or non-RT RIC.

Example 20 includes the computer-readable storage medium of example 18, wherein the plurality of AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and performance metrics of respective communication related algorithms implemented by the plurality of UEs.

Example 21 includes the computer-readable storage medium of example 14, wherein the plurality of offline trained AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and results of respective communication related algorithms implemented by the plurality of UEs.

Example 22 includes the computer-readable storage medium of example 14, wherein the RAN measurement results associated with the UE include a channel quality metric on an uplink or a downlink associated with the UE.

Example 23 includes the computer-readable storage medium of example 22, wherein the channel quality metric comprises a Reference Signal Received Power (RSRP) measurement or a signal to interference plus noise ratio (SINR) measurement.

Example 24 includes the computer-readable storage medium of example 14, wherein the algorithm selection is to instruct a channel estimation algorithm or a beamforming algorithm.

Example 25 includes the computer-readable storage medium of example 14, wherein the algorithm selects a backoff value for indicating a Modulation Coding Scheme (MCS).

Example 26 includes the computer-readable storage medium of example 14, wherein the algorithm selection is to indicate a resource management plan.

Example 27 includes a method in a Radio Access Network (RAN) intelligent controller (RIC), comprising: determining policy guidelines, algorithm selections, or model recommendations based on RAN measurements associated with User Equipment (UE) and location or mobility related information; and providing the policy guidance, the algorithm selection, or the model recommendation to an E2 node for use when the RAN communicates with the UE, wherein the policy guidance is for indicating a policy for determining communication-related operations, the algorithm selection is for indicating a communication-related algorithm, and the model recommendation is for indicating one of a plurality of offline trained Artificial Intelligence (AI) or Machine Learning (ML) models to implement the communication-related algorithm.

Example 28 includes the method of example 27, wherein the policy directive is determined using an AI or ML model deployed in a service application running on the RIC, the AI or ML model configured to estimate performance metrics for respective communication-related operations based on RAN measurements and location or mobility-related information associated with the UE and to output the policy directive, and the communication-related operations determined based on the policy directive indicated by the policy directive have the best performance metrics.

Example 29 includes the method of example 28, wherein the RIC is a near Real Time (RT) RIC and the AI or ML model is trained in the near RT RIC or a non-RT RIC.

Example 30 includes the method of example 29, wherein the AI or ML model is trained based on RAN measurements and location or mobility-related information associated with a plurality of UEs and performance metrics of respective communication-related operations implemented by the plurality of UEs.

Example 31 includes the method of example 27, wherein the algorithm selection is determined using a plurality of AI or ML models deployed in a service application running on the RIC, the plurality of AI or ML models respectively associated with a plurality of communication-related algorithms, each of the plurality of AI or ML models configured to output performance metrics for the respective communication-related algorithm based on RAN measurements and location or mobility-related information associated with the UE, and the communication-related algorithm indicated by the algorithm selection has the best performance metrics.

Example 32 includes the method of example 31, wherein the RIC is a near Real Time (RT) RIC and the plurality of AI or ML models are trained in the near RT RIC or non-RT RIC.

Example 33 includes the method of example 31, wherein the plurality of AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and performance metrics of respective communication related algorithms implemented by the plurality of UEs.

Example 34 includes the method of example 27, wherein the plurality of offline trained AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and results of respective communication related algorithms implemented by the plurality of UEs.

Example 35 includes the method of example 27, wherein the RAN measurement results associated with the UE include channel quality metrics on an uplink or a downlink associated with the UE.

Example 36 includes the method of example 35, wherein the channel quality metric comprises a Reference Signal Received Power (RSRP) measurement or a signal-to-interference-and-noise ratio (SINR) measurement.

Example 37 includes the method of example 27, wherein the algorithm selection is to indicate a channel estimation algorithm or a beamforming algorithm.

Example 38 includes the method of example 27, wherein the algorithm selects a backoff value to indicate a Modulation Coding Scheme (MCS).

Example 39 includes the method of example 27, wherein the algorithm selection is to indicate a resource management plan.

Example 40 includes an apparatus for use in a Radio Access Network (RAN) intelligent controller (RIC), comprising means for implementing the method of any of examples 27 to 39.

Example 41 includes a Radio Access Network (RAN) intelligent controller (RIC) comprising processor circuitry configured to implement the method of any of examples 27 to 39.

Although certain embodiments have been illustrated and described herein for purposes of description, a wide variety of alternate and/or equivalent embodiments or implementations calculated to achieve the same purposes may be substituted for the embodiments shown and described without departing from the scope of the present application. This disclosure is intended to cover any adaptations or variations of the embodiments discussed herein. Accordingly, the embodiments described herein are obviously limited only by the following claims and equivalents thereof.

Claims (25)

1. An apparatus for use in a Radio Access Network (RAN) intelligent controller (RIC), wherein the apparatus comprises a processor circuit configured to cause the RIC to:

Determining policy guidelines, algorithm selections, or model recommendations based on RAN measurements associated with User Equipment (UE) and location or mobility related information; and

providing the policy guidance, the algorithm selection, or the model recommendation to an E2 node for use when the RAN communicates with the UE, wherein

The policy guidelines are for indicating a policy for determining communication-related operations, the algorithm selected for indicating a communication-related algorithm, the model recommended for indicating one of a plurality of offline trained Artificial Intelligence (AI) or Machine Learning (ML) models to implement the communication-related algorithm.

2. The apparatus of claim 1, wherein the policy directive is determined using an AI or ML model deployed in a service application running on the RIC, the AI or ML model configured to estimate performance metrics for respective communication-related operations based on RAN measurements and location or mobility-related information associated with the UE and to output the policy directive, and the communication-related operations determined based on the policy indicated by the policy directive have optimal performance metrics.

3. The apparatus of claim 2, wherein the RIC is a near real-time (RT) RIC, the AI or ML model being trained in the near RT RIC or non-RT RIC.

4. The apparatus of claim 3, wherein the AI or ML model is trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and performance metrics of respective communication related operations implemented by the plurality of UEs.

5. The apparatus of claim 1, wherein the algorithm selection is determined using a plurality of AI or ML models deployed in a service application running on the RIC, the plurality of AI or ML models respectively associated with a plurality of communication-related algorithms, each of the plurality of AI or ML models configured to output performance metrics for the respective communication-related algorithm based on RAN measurements and location or mobility-related information associated with the UE, and the communication-related algorithm indicated by the algorithm selection has the best performance metric.

6. The apparatus of claim 5, wherein the RIC is a near real-time (RT) RIC, the plurality of AI or ML models being trained in the near RT RIC or non-RT RIC.

7. The apparatus of claim 5, wherein the plurality of AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and performance metrics of respective communication related algorithms implemented by the plurality of UEs.

8. The apparatus of claim 1, wherein the plurality of offline trained AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and results of respective communication related algorithms implemented by the plurality of UEs.

9. The apparatus of claim 1, wherein the RAN measurement results associated with the UE comprise channel quality metrics on an uplink or a downlink associated with the UE.

10. The apparatus of claim 9, wherein the channel quality metric comprises a Reference Signal Received Power (RSRP) measurement or a signal-to-interference-and-noise ratio (SINR) measurement.

11. The apparatus of claim 1, wherein the algorithm selection is used to indicate a channel estimation algorithm or a beamforming algorithm.

12. The apparatus of claim 1, wherein the algorithm selects a backoff value for indicating a Modulation Coding Scheme (MCS).

13. The apparatus of claim 1, wherein the algorithm selection is to indicate a resource management plan.

14. A computer readable storage medium having stored thereon computer executable instructions, wherein the computer executable instructions, when executed by processor circuitry of a Radio Access Network (RAN) intelligent controller (RIC), cause the RIC to:

Determining policy guidelines, algorithm selections, or model recommendations based on RAN measurements associated with User Equipment (UE) and location or mobility related information; and

providing the policy guidance, the algorithm selection, or the model recommendation to an E2 node for use when the RAN communicates with the UE, wherein

The policy guidelines are for indicating a policy for determining communication-related operations, the algorithm selected for indicating a communication-related algorithm, the model recommended for indicating one of a plurality of offline trained Artificial Intelligence (AI) or Machine Learning (ML) models to implement the communication-related algorithm.

15. The computer-readable storage medium of claim 14, wherein the policy directive is determined using an AI or ML model deployed in a service application running on the RIC, the AI or ML model configured to estimate performance metrics for respective communication-related operations based on RAN measurements and location or mobility-related information associated with the UE and to output the policy directive, and the communication-related operations determined based on the policy indicated by the policy directive have the best performance metrics.

16. The computer-readable storage medium of claim 15, wherein the RIC is a near real-time (RT) RIC, the AI or ML model being trained in the near RT RIC or non-RT RIC.

17. The computer-readable storage medium of claim 16, wherein the AI or ML model is trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and performance metrics of respective communication related operations implemented by the plurality of UEs.

18. The computer-readable storage medium of claim 14, wherein the algorithm selection is determined using a plurality of AI or ML models deployed in a service application running on the RIC, the plurality of AI or ML models respectively associated with a plurality of communication-related algorithms, each of the plurality of AI or ML models configured to output a performance metric for the respective communication-related algorithm based on RAN measurements and location or mobility-related information associated with the UE, and the communication-related algorithm indicated by the algorithm selection has the best performance metric.

19. The computer-readable storage medium of claim 18, wherein the RIC is a near real-time (RT) RIC, the plurality of AI or ML models being trained in the near RT RIC or non-RT RIC.

20. The computer-readable storage medium of claim 18, wherein the plurality of AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and performance metrics of respective communication related algorithms implemented by the plurality of UEs.

21. The computer-readable storage medium of claim 14, wherein the plurality of offline trained AI or ML models are trained based on RAN measurements and location or mobility related information associated with a plurality of UEs and results of respective communication related algorithms implemented by the plurality of UEs.

22. The computer-readable storage medium of claim 14, wherein the RAN measurement associated with the UE comprises a channel quality metric on an uplink or a downlink associated with the UE.

23. The computer-readable storage medium of claim 22, wherein the channel quality metric comprises a Reference Signal Received Power (RSRP) measurement or a signal to interference plus noise ratio (SINR) measurement.

24. The computer-readable storage medium of claim 14, wherein the algorithm selection is to instruct a channel estimation algorithm or a beamforming algorithm.

25. The computer-readable storage medium of claim 14, wherein the algorithm selects a backoff value for indicating a Modulation Coding Scheme (MCS).