System and method for optimizing radio frequency channel reconfiguration in communication network

Abstract

To provide a system and a method for optimizing radio frequency (RF) reconfiguration within an open radio access network (O-RAN) by service management and orchestration (SMO) framework.SOLUTION: A method includes collecting O1-related data collected between an E2 node and an open radio unit (O-RU) from the E2 node, retraining an AI / ML model based on the O1-related data, deploying and activating one retrained AI / ML model to infer data providing an O1 configuration required to perform RF channel reconfiguration in the O-RAN, monitoring and evaluating the O1-related data providing the O1 configuration required to perform the RF channel reconfiguration, determining to generate O1 configuration data to prepare and perform the RF channel reconfiguration, sending it to the E2 node, and implementing the RF channel reconfiguration in the O-RAN.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] Systems and methods consistent with embodiments of the present disclosure relate to generating and deploying optimized radio frequency (RF) channel reconfigurations in m-MIMO antennas to conserve energy in communication networks. [Background technology]

[0002] The Radio Access Network (RAN) is a critical component in a communication system that connects end-user devices (or user equipment) to the rest of the network. The RAN includes a combination of various network elements (NEs) that connect end-user devices to the core network. Traditionally, the hardware and / or software of a particular RAN has been vendor-specific.

[0003] The emergence of Open RAN (O-RAN) technology allows multiple vendors to provide hardware and / or software for communication systems. To this end, O-RAN decomposes RAN functions into an Open Centralized Unit (O-CU), an Open Distributed Unit (O-DU), and an Open Radio Unit (O-RU). The O-CU is a logical node for hosting the RAN sublayers of Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), and / or Packet Data Convergence Protocol (PDCP). The O-DU is a logical node for hosting the O-RAN sublayers of Radio Link Control (RLC), Medium Access Control (MAC), and Physical (PHY). The O-RU is a physical node that converts radio signals from the antennas into digital signals that can be transmitted over the fronthaul to the O-DU. These entities can be developed by different vendors because of the open protocols and interfaces between them. Summary of the Invention [Problem to be solved by the invention]

[0004] In related technology O-RAN, massive multiple-input multiple-output (m-MIMO) antennas are used for beamforming techniques to increase cell capacity and traffic throughput. To achieve beamforming, the RU must concentrate power amplifiers at the antenna site by combining radiating elements such as transmitter / receiver (Tx / Rx) arrays.

[0005] In related art, up to 64 transmitter / receiver (Tx / Rx) arrays can be deployed to maximize cell capacity and traffic throughput, where the larger the number of Tx / Rx arrays, the greater the cell capacity and traffic throughput. In this case, the m-MIMO antennas also consume the maximum energy for beamforming.

[0006] A maximum of 64 transmitter / receiver (Tx / Rx) arrays are preferably used as the standard setting for m-MIMO antennas in the related art. This maximum beamforming has the drawback that in the case of low O-RAN load, i.e., when the expected traffic volume or number of connected users is lower than a configured threshold, the high power consumption of the RU due to maximum use of the Tx / Rx arrays results in energy-inefficient operation of the RU within the O-RAN. [Means for solving the problem]

[0007] According to an embodiment, a system and method are provided for implementing optimization of radio frequency (RF) channel reconfiguration in m-MIMO antennas in an O-RAN through an open radio access network and service management and orchestration (SMO). The SMO includes a non-real-time RAN intelligent controller (NRT-RIC), an NRT-RIC framework, at least one SMO function, and an rApp hosted by the NRT-RIC. The rApp generates and implements O1 configuration data for preparing and executing RF channel reconfiguration in m-MIMO antennas by one or more E2 nodes (i.e., O-RUs via E-nodes). With the assistance of artificial intelligence / machine learning (AI / ML) techniques, O1-related data from the E2 nodes (i.e., from the O-RUs via the E2 nodes) is used to retrain, deploy, and activate AI / ML models to infer data providing the O1 configuration required to perform RF channel reconfiguration in m-MIMO antennas in the O-RUs. The RF channel reconfiguration control provides the O1 configuration required to perform RF channel reconfiguration in the O-RUs and considers network-wide energy efficiency instead of local optimization in the O-RAN. According to an embodiment, the system and method enable energy savings (ES) by reducing the power consumption of an O-RU through RF channel reconfiguration (e.g., by switching off certain transmitter / receiver (Tx / Rx) arrays).

[0008] For example, when the network load is low (i.e., when the expected traffic volume or number of connected users is lower than a configured threshold), ES can be achieved by reducing the power consumption of the O-RU, e.g., by switching off 32 of the 64 Tx / Rx arrays of the O-RU in a digital m-MIMO architecture and reducing the number of corresponding spatial layers and synchronization signal blocks (SSBs).The RF channel reconfiguration procedure (i.e., the involvement of each O-RAN interface) depends on the management architecture model (hybrid or hierarchical) and deployment options.

[0009] The RF channel reconfiguration decision may be made by an AI / ML model in an inference host deployed in the NRT-RIC or near real-time RAN intelligent controller (nRT-RIC). The AI / ML model may include predictions of future traffic, user mobility, and resource usage in addition to other parameters (i.e., forecast data), and may predict expected energy efficiency improvements, resource usage, and network performance for different ES optimization states.

[0010] As a result, the systems and methods implement an NRT-RIC framework that allows network operators to flexibly configure on / off switching parameters for RF channel reconfiguration (e.g., for switching on / off Tx / Rx arrays in m-MIMO antennas in O-RUs) to optimize network-wide energy efficiency instead of local optimization in O-RAN.

[0011] According to an embodiment, a system for implementing radio frequency (RF) reconfiguration optimization via a service management and orchestration (SMO) framework within an open radio access network (O-RAN) is provided. The system includes a memory storing instructions and at least one processor configured to implement a non-real-time RAN intelligent controller (NRT-RIC), an NRT-RIC framework, at least one SMO function, and an rApp hosted by the NRT-RIC.The at least one processor, via an rApp, collects O1-related data from the E2 node via an R1 interface through the NRT-RIC framework and via an SMO function within the SMO framework, the O1-related data providing an O1 configuration required to perform RF channel reconfiguration, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the open radio unit (O-RU); retrains, via the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; and deploys and activates, via the rApp, one retrained AI / ML model from the at least one retrained AI / ML to infer data providing an O1 configuration required to perform RF channel reconfiguration within the O-RAN; and deploys, via the rApp, one retrained AI / ML model from the at least one retrained AI / ML to infer data providing an O1 configuration required to perform RF channel reconfiguration within the O-RAN. and executing instructions to: monitor, via an rApp, O1-related data that provides an O1 configuration required to perform RF channel reconfiguration via an O1 interface through the NRT-RIC framework; evaluate, via the rApp, the O1-related data that provides the O1 configuration required to perform RF channel reconfiguration; determine, via the rApp, to generate O1 configuration data for preparing and performing RF channel reconfiguration; send, via the rApp, the O1 configuration data for preparing and performing RF channel reconfiguration to at least one E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through at least one SMO function in the SMO framework; and implement, by the E2 node and the O-RU, RF channel reconfiguration in the O-RAN. The at least one processor is further configured, during implementation, to convert, by the E2 node, the O1 configuration data for preparing and performing RF channel reconfiguration, and instruct, by the E2 node, via an open FH M-Plane, the O1 configuration data to the O-RU to perform RF channel reconfiguration.

[0012] The at least one processor may be further configured to, during retraining of the at least one AI / ML model, select, by the rApp, an AI / ML model from the plurality of AI / ML models; send, by the rApp, an initiation request to retrain the AI / ML model to the NRT-RIC framework; retrain, by the NRT-RIC framework, the AI / ML model; monitor, by the rApp, the retrained AI / ML model parameters; determine, based on the retrained AI / ML model parameters, to retrieve the retrained AI / ML model from the NRT-RIC framework; request, by the rApp, the retrained AI / ML model from the NRT-RIC framework; and send, by the NRT-RIC framework, the retrained AI / ML model to the rApp.

[0013] The at least one processor may be further configured to, during retraining of the at least one AI / ML model, retrain one AI / ML model from the plurality of AI / ML models by the rApp.

[0014] The O1-related data providing the O1 configuration necessary to perform RF channel reconfiguration may include at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU. The measurement report may include at least one of an energy efficiency / energy consumption (EE / EC) measurement report. The energy efficiency / energy consumption (EE / EC) measurement report may include at least one of Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell, Reference Signal Received Power (RSRP) measurements per SSB per cell, Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell, energy consumption, power consumed by hardware components, transmit power, per-cell and per-carrier load statistics (such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, Precoding Matrix Indicator / Channel State Information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs).

[0015] The at least one processor may be configured to: during collection of O1-related data that provides the O1 configuration required to perform RF channel reconfiguration, send, by the rApp, an O1-related data collection request to the E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through an SMO function in the SMO framework; receive, by the E2 node, the O1-related data collection request from the SMO function; collect, by the E2 node, O1-related data that provides the O1 configuration required to perform RF channel reconfiguration from the O-RU via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU; and send, by the E2 node, the O1-related data that provides the O1 configuration required to perform RF channel reconfiguration that has been collected via the O1 interface through the SMO function in the SMO framework and the NRT-RIC framework to the rApp via the R1 interface.

[0016] The O1 configuration data for preparing and performing RF channel reconfiguration may include at least one of O-RU Tx / Rx array selection, changing the number of SU / MU MIMO spatial streams or data layers, changing the number of SSB beams, and changing the O-RU antenna transmit power.

[0017] The at least one processor may be further configured to monitor, by the NRT-RIC, the performance of the retrained AI / ML model, determine that predetermined performance goals are not achieved based on the collected O1-related data, and initiate a fallback mechanism and / or an update or retraining of the AI / ML model.

[0018] According to an embodiment, a method for implementing radio frequency (RF) reconfiguration optimization via a service management and orchestration (SMO) framework within an open radio access network (O-RAN) is provided. The method includes: collecting, by an rApp, O1-related data from an E2 node via an R1 interface through an NRT-RIC framework and via an SMO function within the SMO framework, the O1-related data providing an O1 configuration required to perform RF channel reconfiguration, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between an E2 node and an open radio unit (O-RU); retraining, by the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; deploying and activating, by the rApp, one of the at least one retrained AI / ML model for inferring data providing an O1 configuration required to perform RF channel reconfiguration within the O-RAN; and transmitting, by the rApp, O1-related data via the R1 interface through the NRT-RIC framework and via an SMO function within the SMO framework. monitoring, via an MO function, via an O1 interface, O1-related data that provides the O1 configuration required to perform RF channel reconfiguration; evaluating, via the rApp, the O1-related data that provides the O1 configuration required to perform RF channel reconfiguration; determining, via the rApp, to generate O1 configuration data for preparing and performing RF channel reconfiguration; sending, via the rApp, the O1 configuration data for preparing and performing RF channel reconfiguration to at least one E2 node via an R1 interface through an NRT-RIC framework and via an O1 interface through at least one SMO function in an SMO framework; and implementing, by the E2 node and the O-RU, the RF channel reconfiguration in the O-RAN.The implementing includes: converting, by the E2 node, O1 configuration data for preparing and performing RF channel reconfiguration; and instructing, by the E2 node, via an open FH M-Plane, the O-RU to perform RF channel reconfiguration.

[0019] Retraining at least one AI / ML model includes selecting, by the rApp, an AI / ML model from the plurality of AI / ML models; sending, by the rApp, an initiation request to retrain the AI / ML model to the NRT-RIC framework; retraining, by the NRT-RIC framework, the AI / ML model; monitoring, by the rApp, retrained AI / ML model parameters and determining, based on the retrained AI / ML model parameters, to retrieve the retrained AI / ML model from the NRT-RIC framework; requesting, by the rApp, the retrained AI / ML model from the NRT-RIC framework; and sending, by the NRT-RIC framework, the retrained AI / ML model to the rApp.

[0020] Retraining at least one AI / ML model includes retraining one AI / ML model from the plurality of AI / ML models by the rApp.

[0021] The O1-related data providing the O1 configuration necessary to perform RF channel reconfiguration may include at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU. The measurement report may include at least one of an energy efficiency / energy consumption (EE / EC) measurement report. The energy efficiency / energy consumption (EE / EC) measurement report may include at least one of Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell, Reference Signal Received Power (RSRP) measurements per SSB per cell, Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell, energy consumption, power consumed by hardware components, transmit power, per-cell and per-carrier load statistics (such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, Precoding Matrix Indicator / Channel State Information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs).

[0022] Collecting O1-related data that provides an O1 configuration necessary to perform RF channel reconfiguration includes sending, by the rApp, an O1-related data collection request to the E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through an SMO function in the SMO framework; receiving, by the E2 node, the O1-related data collection request from the SMO function; collecting, by the E2 node, O1-related data from an open radio unit (O-RU) via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU that provides the O1 configuration necessary to perform RF channel reconfiguration; and sending, by the E2 node, the O1-related data that provides the O1 configuration necessary to perform RF channel reconfiguration that has been collected via the O1 interface through the SMO function in the SMO framework and the NRT-RIC framework to the rApp via the R1 interface.

[0023] The O1 configuration data for preparing and performing RF channel reconfiguration may include at least one of O-RU Tx / Rx array selection, changing the number of SU / MU MIMO spatial streams or data layers, changing the number of SSB beams, and changing the O-RU antenna transmit power.

[0024] The method may further include monitoring, by the NRT-RIC, performance of the retrained AI / ML model, determining that predetermined performance goals are not achieved based on the collected O1-related data, and initiating a fallback mechanism and / or updating or retraining the AI / ML model.

[0025] According to an embodiment, there is provided a non-transitory computer-readable storage medium having stored thereon instructions executable by at least one processor configured to implement a Non-Real-Time RAN Intelligent Controller (NRT-RIC), an NRT-RIC framework, at least one SMO function, and an rApp hosted by the NRT-RIC to perform a method for implementing optimization of radio frequency (RF) reconfiguration via a service management and orchestration (SMO) framework within an Open Radio Access Network (O-RAN).The method includes: collecting, by an rApp, O1-related data from an E2 node via an R1 interface through an NRT-RIC framework and via an O1 interface through an SMO function within an SMO framework, the O1-related data providing an O1 configuration required to perform RF channel reconfiguration, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between an E2 node and an open radio unit (O-RU); retraining, by the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; deploying and activating, by the rApp, one retrained AI / ML model from the at least one retrained AI / ML to infer data providing an O1 configuration required to perform RF channel reconfiguration within the O-RAN; and transmitting, by the rApp, O1-related data from the E2 node via an R1 interface through the NRT-RIC framework and via an SMO function within the SMO framework. and implementing, by the E2 node and the O-RU, the RF channel reconfiguration in the O-RAN. The implementing includes converting, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration, and instructing, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration. The O1 configuration data includes converting, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration, and instructing, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration via an open FH M-Plane.

[0026] Retraining at least one AI / ML model includes selecting, by the rApp, an AI / ML model from the plurality of AI / ML models; sending, by the rApp, an initiation request to retrain the AI / ML model to the NRT-RIC framework; retraining, by the NRT-RIC framework, the AI / ML model; monitoring, by the rApp, retrained AI / ML model parameters and determining, based on the retrained AI / ML model parameters, to retrieve the retrained AI / ML model from the NRT-RIC framework; requesting, by the rApp, the retrained AI / ML model from the NRT-RIC framework; and sending, by the NRT-RIC framework, the retrained AI / ML model to the rApp.

[0027] Retraining at least one AI / ML model includes retraining one AI / ML model from the plurality of AI / ML models by the rApp.

[0028] The O1-related data providing the O1 configuration necessary to perform RF channel reconfiguration may include at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU. The measurement report may include at least one of an energy efficiency / energy consumption (EE / EC) measurement report. The energy efficiency / energy consumption (EE / EC) measurement report may include at least one of Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell, Reference Signal Received Power (RSRP) measurements per SSB per cell, Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell, energy consumption, power consumed by hardware components, transmit power, per-cell and per-carrier load statistics (such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, Precoding Matrix Indicator / Channel State Information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs).

[0029] Collecting O1-related data that provides an O1 configuration necessary to perform RF channel reconfiguration includes sending, by the rApp, an O1-related data collection request to the E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through an SMO function in the SMO framework; receiving, by the E2 node, the O1-related data collection request from the SMO function; collecting, by the E2 node, O1-related data from an open radio unit (O-RU) via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU that provides the O1 configuration necessary to perform RF channel reconfiguration; and sending, by the E2 node, the O1-related data that provides the O1 configuration necessary to perform RF channel reconfiguration that has been collected via the O1 interface through the SMO function in the SMO framework and the NRT-RIC framework to the rApp via the R1 interface.

[0030] The O1 configuration data for preparing and performing RF channel reconfiguration may include at least one of O-RU Tx / Rx array selection, changing the number of SU / MU MIMO spatial streams or data layers, changing the number of SSB beams, and changing the O-RU antenna transmit power.

[0031] The method may further include monitoring, by the NRT-RIC, performance of the retrained AI / ML model, determining that predetermined performance goals are not achieved based on the collected O1-related data, and initiating a fallback mechanism and / or updating or retraining the AI / ML model.

[0032] Additional aspects will be set forth in part in the description that follows, and in part will be obvious from the description, or may be realized by practice of presented embodiments of the disclosure. [Brief explanation of the drawings]

[0033] Features, aspects, and advantages of certain exemplary embodiments of the disclosure are described below with reference to the accompanying drawings, in which like reference numerals represent like elements.

[0034] FIG. 1 illustrates an O-RAN architecture in the related art.

[0035] FIG. 2 is a diagram of an example environment in which the systems and / or methods described herein may be implemented.

[0036] FIG. 3 is a diagram of example components of a device according to one embodiment.

[0037] FIG. 4 illustrates an NRT-RIC framework within an O-RAN according to one embodiment.

[0038] FIG. 5 is a flow diagram of a method for implementing RF reconfiguration optimization according to one embodiment.

[0039] FIG. 6 illustrates a data collection flow according to one embodiment.

[0040] FIG. 7 illustrates the data analysis, training and inference flow of an AI / ML model according to one embodiment.

[0041] FIG. 8 illustrates a data analysis, AI / ML model training and inference flow according to another embodiment.

[0042] FIG. 9 illustrates the generation and implementation of O1 configuration data for preparing and performing RF channel reconfiguration for m-MIMO antennas in an O-RU according to one embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0043] The following detailed description of the embodiments refers to the accompanying drawings. The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit implementations to the precise form disclosed. Modifications and variations are possible in light of the foregoing disclosure or may be acquired from practice of the implementations. Furthermore, one or more features or components of one embodiment may be combined or combined with other embodiments (or one or more features of other embodiments). Additionally, in the flowcharts and operational descriptions provided below, it is understood that one or more operations may be omitted, one or more operations may be added, one or more operations may be performed concurrently (at least in part), and the order of one or more operations may be rearranged.

[0044] It will be apparent that the systems and / or methods described herein may be implemented in different forms of hardware, firmware, or a combination of hardware and software. The actual specific control hardware or software code used to implement these systems and / or methods is not a limitation of the implementation. Thus, the operation and behavior of the systems and / or methods are described herein without reference to specific software code. It will be understood that software and hardware may be designed to implement the systems and / or methods based on the description herein.

[0045] Although particular feature combinations are recited in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of possible implementations. Indeed, many of these features may be combined in ways other than those specifically recited in the claims and / or specifically disclosed in the specification. Although each dependent claim listed below may depend directly on only one claim, the disclosure of possible implementations includes each dependent claim in combination with all other claims in the claim group.

[0046] No element, act, or instruction used herein should be construed as critical or required unless explicitly stated otherwise. Also, as used herein, the articles "a" and "an" are intended to include one or more items and may be used interchangeably with "one or more." Where only one item is intended, the term "one" or similar words are used. Also, as used herein, the terms "has," "have," "having," "include," "including," etc. are intended to be open-ended terms. Furthermore, the phrase "based on" is intended to mean "based, at least in part, on," unless expressly stated otherwise. Furthermore, phrases such as "at least one of A and B" or "at least one of A or B" are understood to include A only, B only, or both A and B.

[0047] Embodiments of the present disclosure provide a system and method in which the NRT-RIC framework and / or rApp configure RF channel reconfiguration parameters (e.g., for switching on / off the Tx / Rx arrays in an m-MIMO antenna in an O-RU) that enable flexible RF channel reconfiguration, for example, via an A1 policy or optimization trigger over the O1 interface to the nRT-RIC defined by the NRT-RIC (i.e., by at least one rApp hosted by the NRT-RIC and / or the NRT-RIC framework assisted by machine learning (ML) techniques). Actions of the nRT-RIC over the E2 interface may enable deployment of O1 configuration data to prepare and perform RF channel reconfiguration for one or more E2 nodes. Implementation based on the O1 configuration data for preparing and performing cell and RF channel reconfiguration in the O-RU is initiated by the E2 node over the open FH M-Plane interface between the E2 node and the O-RU.

[0048] For this purpose, before applying the RF channel reconfiguration (e.g., switching on / off the Tx / Rx array), the E2 node may need to perform preparatory actions for the RF channel reconfiguration. For example, the E2 node may check per-cell and per-carrier load statistics (number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, precoding matrix indicator / channel state information (PMI / CSI) reports, etc.). Furthermore, the E2 node may check per-cell latency statistics (e.g., when Ultra-Reliable Low Latency Communication (URLLC) slices are involved, latency is used to define energy efficiency (EE)).

[0049] Figure 1 illustrates an O-RAN architecture in the related art. Referring to Figure 1, RAN functions in the O-RAN architecture are controlled and optimized by RICs. RICs are software-defined components that implement modular applications to realize the multi-vendor operability required in O-RAN systems and automate and optimize RAN operations. RICs are divided into two types: non-real-time RICs (NRT-RICs) and near-real-time RICs (nRT-RICs).

[0050] The NRT-RIC is the control point for non-real-time control loops and operates within a Service Management and Orchestration (SMO) framework on timescales longer than one second. Its functions are implemented through modular applications called rApps (rApp 1, ..., rApp N) and include providing policy-based guidance and enrichment over the A1 interface, which is the interface enabling communication between the NRT-RIC and nRT-RIC; performing data analytics; artificial intelligence / machine learning (AI / ML) training and inference for RAN optimization; and / or recommending configuration management actions over the O1 interface, which is the interface connecting the SMO to RAN management elements (e.g., nRT-RIC, O-RAN aggregation unit (O-CU), O-RAN distributed unit (O-DU), etc.).

[0051] The nRT-RIC operates on a time scale between 10 milliseconds and 1 second and connects to the O-DU, O-CU (decomposed into the O-CU control plane (O-CU-CP) and the O-CU user plane (O-CU-UP)), and open evolved NodeB (O-eNB) via the E2 interface. The nRT-RIC uses the E2 interface to control the underlying RAN elements (E2 nodes / network functions (NFs)) in a near-real-time control loop. The nRT-RIC monitors, suspends / stops, overrides, and controls the E2 nodes (O-CU, O-DU, and O-eNB) through policies. For example, the nRT-RIC sets policy parameters on the activated functions of the E2 nodes. Furthermore, the nRT-RIC hosts xApps for implementing functions such as quality of service (QoS) optimization, mobility optimization, slicing optimization, interference mitigation, load balancing, and security. The two types of RICs work together to optimize the O-RAN. For example, the NRT-RIC provides policies, data, and artificial intelligence / machine learning (AI / ML) models over the A1 interface that are enabled and used by the nRT-RIC for RAN optimization, and the nRT-RIC returns policy feedback (i.e., how the policies set by the NRT-RIC are working).

[0052] The SMO framework in which the NRT-RIC resides manages and coordinates RAN elements. Specifically, the SMO manages and coordinates what is referred to as the O-RAN Cloud (O-Cloud). The O-Cloud is a collection of physical RAN nodes that host the RIC, O-CU, and O-DU, supporting software components (e.g., operating systems and runtime environments), and the SMO itself. In other words, the SMO manages the O-Cloud from within. The O2 interface is the interface between the SMO and the O-Cloud in which it resides. The SMO provides Infrastructure Management Services (IMS) and Deployment Management Services (DMS) through the O2 interface.

[0053] On the other hand, the O-Cloud is a cloud computing platform that comprises a collection of physical infrastructure nodes that meet the O-RAN specifications for hosting the relevant O-RAN functions (e.g., nRT-RIC, O-CU-CP, O-CU-UP, O-DU, etc.), supporting software components (operating systems, virtual machine monitors, container runtimes, etc.) and appropriate management and orchestration functions.

[0054] The SMO framework, where the NRT-RIC is located, manages and orchestrates RAN elements. The SMO performs management and orchestration of RAN elements through four key interfaces: the A1 interface for RAN optimization between the NRT-RIC and nRT-RIC in the SMO; the O1 interface for FCAPS support between the SMO and O-RAN network functions; the open fronthaul M-plane interface for FCAPS support between the SMO and O-RU in the hybrid model; and the O2 interface for platform resource and workload management between the SMO and O-Cloud.

[0055] 2 is a diagram of an example environment 200 in which the systems and / or methods described herein may be implemented. As shown in FIG. 2, environment 200 may include a user device 210, a platform 220, and a network 230. The devices of environment 200 may be interconnected via wired connections, wireless connections, or a combination of wired and wireless connections. In an embodiment, any of the functions and operations described above with reference to FIG. 1 may be performed by any combination of elements illustrated in FIG. 2.

[0056] User device 210 includes one or more devices capable of receiving, generating, storing, processing, and / or providing information related to platform 220. For example, user device 210 may include a computing device (e.g., a desktop computer, a laptop computer, a tablet computer, a handheld computer, a smart speaker, a server, etc.), a mobile phone (e.g., a smartphone, a wireless phone, etc.), a wearable device (e.g., smart glasses or a smart watch), or similar device. In some implementations, user device 210 may receive information from and / or send information to platform 220.

[0057] Platform 220 includes one or more devices capable of receiving, generating, storing, processing, and / or providing information. In some implementations, platform 220 may include a cloud server or a group of cloud servers. In some implementations, platform 220 may be designed to be modular, such that particular software components may be swapped in or out depending on particular needs. In this manner, platform 220 may be easily and / or quickly reconfigured for different uses.

[0058] In some implementations, as shown, platform 220 may be hosted in a cloud computing environment 222. Note that although the implementations described herein describe platform 220 as being hosted in a cloud computing environment 222, in some implementations platform 220 may not be cloud-based (i.e., may be implemented outside of a cloud computing environment) or may be partially cloud-based.

[0059] Cloud computing environment 222 includes an environment that hosts platform 220. Cloud computing environment 222 may provide services such as computation, software, data access, storage, etc., without requiring end-user (e.g., user device 210) knowledge of the physical location and configuration of the systems and / or devices that host platform 220. As shown, cloud computing environment 222 may include a group of computing resources 224 (collectively referred to as “computing resources 224” and individually referred to as “computing resource 224”).

[0060] Computing resources 224 include one or more personal computers, clusters of computing devices, workstation computers, server devices, or other types of computation and / or communication devices. In some implementations, computing resources 224 may host platform 220. Cloud resources may include compute instances executing on computing resources 224, storage devices provided on computing resources 224, data transfer devices provided by computing resources 224, etc. In some implementations, computing resources 224 may communicate with other computing resources 224 via wired connections, wireless connections, or a combination of wired and wireless connections.

[0061] As further shown in FIG. 2, computing resources 224 include a group of cloud resources such as one or more applications (“APP”) 224-1, one or more virtual machines (“VM”) 224-2, virtualized storage (“VS”) 224-3, and one or more hypervisors (“HYP”) 224-4.

[0062] Application 224-1 includes one or more software applications that may be provided to or accessed by user device 210. Application 224-1 may obviate the need to install and run a software application on user device 210. For example, application 224-1 may include software associated with platform 220 and / or any other software that may be provided via cloud computing environment 222. In some implementations, one application 224-1 may send or receive information to or from one or more other applications 224-1 via virtual machine 224-2.

[0063] Virtual machine 224-2 includes a software implementation of a device (e.g., a computer) that executes programs like a physical device. Virtual machine 224-2 may be a system virtual machine or a process virtual machine, depending on the use by virtual machine 224-2 and the degree of correspondence with any real-world device. A system virtual machine may provide a complete system platform that supports the execution of a complete operating system (“OS”). A process virtual machine may execute a single program or support a single process. In some implementations, virtual machine 224-2 may execute on behalf of a user (e.g., user device 210) and manage the infrastructure of cloud computing environment 222, such as data management, synchronization, or long-term data transfer.

[0064] Virtualized storage 224-3 includes one or more storage systems and / or one or more devices or computing resources 224 that use virtualization technology within a storage system. In some implementations, within the context of a storage system, types of virtualization may include block virtualization and file virtualization. Block virtualization may represent the abstraction (or separation) of logical storage from physical storage so that the storage system may be accessed without consideration of the physical storage or heterogeneous structure. The separation may provide storage system administrators with flexibility in managing storage for end users. File virtualization may remove the dependency between data accessed at the file level and where the file is physically stored. This may enable storage usage optimization, server consolidation, and / or non-disruptive file migration performance.

[0065] Hypervisor 224-4 may provide hardware virtualization technology that allows multiple operating systems (e.g., "guest operating systems") to run simultaneously on a host computer, such as computing resource 224. Hypervisor 224-4 may present a virtual operating platform to the guest operating systems and may manage the execution of the guest operating systems. Multiple instances of different operating systems may share virtualized hardware resources.

[0066] Network 230 may include one or more wired and / or wireless networks. For example, network 230 may include a cellular network (e.g., a fifth-generation (5G) network, a long-term evolution (LTE) network, a third-generation (3G) network, a code division multiple access (CDMA) network, etc.), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., a public switched telephone network (PSTN), a private network, an ad hoc network, an intranet, the Internet, an optical fiber-based network, etc.), and / or a combination of these or other types of networks.

[0067] The number and arrangement of devices and networks shown in Figure 2 are provided as an example. In practice, there may be additional, fewer, different, or differently arranged devices and / or networks than those shown in Figure 2. Furthermore, two or more devices shown in Figure 2 may be implemented within a single device, and a single device shown in Figure 2 may be implemented as multiple distributed devices. Additionally or alternatively, a set of devices in environment 200 (e.g., one or more devices) may perform one or more functions that are described as being performed by other sets of devices in environment 200.

[0068] 3 is a diagram of example components of a device 300. The device 300 may correspond to the user device 210 and / or the platform 220. As shown in FIG. 3, the device 300 may include a bus 310, a processor 320, a memory 330, a storage component 340, an input component 350, an output component 360, and a communication interface 370.

[0069] The bus 310 includes components that enable communication between the components of the device 300. The processor 320 may be implemented in hardware, firmware, or a combination of hardware and software. The processor 320 may be a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), a microprocessor, a microcontroller, a digital signal processor (DSP), a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or other types of processing components. In some implementations, the processor 320 includes one or more processors that are programmable to perform functions. The memory 330 includes random access memory (RAM), read-only memory (ROM), and / or other types of dynamic or static storage devices (e.g., flash memory, magnetic memory, and / or optical memory) that store information and / or instructions for use by the processor 320.

[0070] Storage component 340 stores information and / or software related to the operation and use of device 300. For example, storage component 340 may include a hard disk (e.g., a magnetic disk, optical disk, magneto-optical disk, and / or solid-state disk), a compact disk (CD), a digital versatile disk (DVD), a floppy disk, a cartridge, magnetic tape, and / or other type of non-transitory computer-readable medium, along with a corresponding drive. Input component 350 includes components that enable device 300 to receive information, such as via user input (e.g., a touchscreen display, a keyboard, a keypad, a mouse, buttons, switches, and / or a microphone). Additionally or alternatively, input component 350 may include sensors for measuring information (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, and / or an actuator). Output component 360 includes components that provide output information from device 300 (e.g., a display, a speaker, and / or one or more light-emitting diodes (LEDs)).

[0071] Communications interface 370 includes transceiver-like components (e.g., a transceiver and / or a separate receiver and transmitter) that allow device 300 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communications interface 370 allows device 300 to receive information from and / or provide information to other devices. For example, communications interface 370 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi interface, a cellular network interface, etc.

[0072] Device 300 may perform one or more processes described herein. Device 300 may perform these processes in response to processor 320 executing software instructions stored by a non-transitory computer-readable medium, such as memory 330 and / or storage component 340. A computer-readable medium is defined herein as a non-transitory memory device. A memory device includes memory space within a single physical storage device or memory space distributed across multiple physical storage devices.

[0073] The software instructions may be loaded into memory 330 and / or storage component 340 from other computer-readable media or other devices via communication interface 370. When executed, the software instructions stored in memory 330 and / or storage component 340 may cause processor 320 to perform one or more of the processes described herein.

[0074] Additionally or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, implementations described herein are not limited to any specific combination of hardware circuitry and software. The number and arrangement of components shown in FIG. 3 are provided as an example. In practice, device 300 may include additional, fewer, different, or differently arranged components than those shown in FIG. 3. Additionally or alternatively, a set of components of device 300 (e.g., one or more components) may perform one or more functions described as being performed by other sets of components of device 300.

[0075] In embodiments, any of the operations or processes of Figures 4, 5, 6, 7, and 8 may be implemented by or using any of the elements illustrated in Figures 1, 2, and 3. It is understood that other embodiments are not so limited and may be implemented in a variety of different architectures (e.g., bare metal architectures, any cloud-based architectures or deployment architectures such as Kubernetes, Docker, OpenStack, etc.).

[0076] FIG. 4 illustrates an NRT-RIC framework (or platform) within an SMO framework system architecture and rApps for the R1 interface hosted by the NRT-RIC, and the O1, O2, and A1 interfaces within the O-RAN, according to one embodiment.

[0077] 4, the NRT-RIC represents a subset of the functionality of the SMO framework. The NRT-RIC has access to other SMO framework functions and can affect (i.e., control and / or perform) what is done across the O1 and O2 interfaces (e.g., performing configuration management (CM) and / or performance management (PM)).

[0078] Generally, FCAPS management, software management, and file management are achieved by the O1 interface for operations and management between management entities (Network Management System (NMS) / Element Management System (EMS) / Management and Orchestration of Network Functions Virtualization (MANO)) and O-RAN management elements.

[0079] The SMO framework system architecture includes SMO functionality including O1 termination that enables communication between the SMO framework and E2 nodes (ie, O-CU, O-DU, etc.) via the O1 interface.

[0080] The NRT-RIC includes an NRT-RIC framework. The NRT-RIC framework includes, among other functions, an R1 service exposure function that handles the R1 services provided in accordance with an embodiment. Generally, the NRT-RIC functions within the NRT-RIC framework support authorization, authentication, registration, discovery, communication support, etc. for rApps.

[0081] Generally, R1 services may include a collection of services including, but not limited to, service registration and discovery services, authentication and authorization services, AI / ML workflow services, and A1, O1 and O2-interface related services.

[0082] An NRT-RIC application (rApp) is an application that utilizes the functionality available in the NRT-RIC framework and / or SMO framework to provide value-added services related to RAN operation and optimization. The scope of an rApp includes, but is not limited to, radio resource management, data analytics, etc., and information enrichment. Generally, an rApp represents an application designed to consume and / or produce R1 services.

[0083] To this end, the NRT-RIC framework produces and / or consumes an R1 service according to an embodiment via an R1 interface, which terminates at an R1 termination in the NRT-RIC framework, which connects to the NRT-RIC framework and rApps via the R1 interface and enables the NRT-RIC framework and rApps to exchange messages / data (i.e., requests and responses comprising a data model) to access the R1 service via the R1 interface.

[0084] Generally, the R1 interface is defined as the interface between the rApp and NRT-RIC frameworks through which R1 services can be produced and consumed.

[0085] Furthermore, the NRT-RIC framework includes A1-related functions, such as supporting A1 logical termination, A1 policy coordination and catalog, and A1-EI coordination and catalog.

[0086] Data management and exposure services within the NRT-RIC framework deliver data generated or collected by data generators to data consumers according to their needs (e.g., Function Management (FM) / Consumption Management (CM) / Production Management (PM) data to rApps or CM changes via the O1 interface from rApps to O-RAN).

[0087] The NRT-RIC framework further comprises an external termination, which supports the exchange of data between the NRT-RIC framework and external AI / ML functions, enrichment information (EI) sources, or external oversight, for example.

[0088] Within the NRT-RIC framework, AI / ML workflow services provide access to AI / ML workflows. For example, the AI / ML workflow services may assist in training models, monitoring AI / ML models deployed in the NRT-RIC, etc.

[0089] Additionally, the NRT-RIC framework provides A2 related functions that support, for example, A2 logical termination, A2 policy coordination and catalogs.

[0090] Still referring to Figure 4, within the NRT-RIC, the R1 interface is an open logical interface within the O-RAN architecture between the rApps and the NRT-RIC framework of the NRT-RIC. The R1 interface supports the exchange of control signaling information and data collection and delivery between endpoints. The R1 interface allows, for example, multi-vendor rApps to consume and / or produce R1 services.

[0091] The R1 interface is independent of the specific implementation of the NRT-RIC framework of the SMO and NRT-RIC. The R1 interface is defined in an extensible manner that allows new services and data types to be added without having to change protocols or procedures.

[0092] In particular, the R1 interface enables interconnection between rApps and NRT-RIC frameworks provided by different vendors (i.e., enables interconnection in a multi-vendor environment). To this end, the R1 interface provides a level of abstraction between the rApps and the NRT-RIC and / or SMO frameworks.

[0093] 4, for example, by an A1 policy or optimization trigger over the O1 interface to the nRT-RIC defined by the NRT-RIC (i.e., by at least one rApp hosted by the NRT-RIC and / or the NRT-RIC framework assisted by machine learning (ML) technology), the NRT-RIC framework (e.g., at least one rApp hosted by the NRT-RIC and / or the NRT-RIC framework) enables flexible RF channel reconfiguration (e.g., to switch on / off Tx / Rx arrays in an m-MIMO antenna in the O-RU). Actions of the nRT-RIC over the E2 interface may enable deployment of RF channel reconfiguration parameters to one or more E2 nodes.

[0094] 4, the SMO framework functionality is configured to collect configurations, performance indicators, and measurement reports (e.g., cell load-related information and traffic information, energy efficiency (EE) measurement reports, energy consumption (EC) measurement reports, etc.) from the E2 node and the O-RU (via the E2 node) for decision-making purposes. Decision-making may be based, for example, on using training and inference of AI / ML models that support such energy efficiency (EE) and / or energy consumption (EC) functionality.

[0095] Generally, energy efficiency (EE) is defined as the relationship between useful output and energy / power consumption, and energy consumption (EC) is defined as the integral of power consumption over time.

[0096] Furthermore, the SMO framework function is configured to forward the collected data to the NRT-RIC framework and signal (i.e., send) updated RF channel reconfiguration parameters and execution of optimization actions to the E2 node via the O1 interface.

[0097] The NRT-RIC framework is configured to collect configurations, performance indicators, and measurement reports (e.g., cell load-related information and traffic information, energy efficiency (EE) measurement reports and / or energy consumption (EC) measurement reports, etc.) for decision-making purposes. Decision-making may be based, for example, on using training and inference of AI / ML models that support such energy efficiency (EE) and / or energy conservation (ES) functions.

[0098] Furthermore, the NRT-RIC framework is configured to forward the collected data (i.e., O1-related data for RF channel reconfiguration parameters (e.g., for switching on / off the Tx / Rx array in the m-MIMO antenna in the O-RU)) to the rApp and signal (i.e., send) the updated configuration for EE / ES optimization to the E2 nodes (i.e., O-CU, O-DU, etc.) through the SMO framework function.

[0099] In one embodiment, the NRT-RIC framework may be configured to retrain, update, and configure EE / ES AI / ML models in the NRT-RIC.

[0100] Still referring to FIG. 4, one or more rApps hosted by the NRT-RIC are configured to retrieve necessary configurations, performance indicators, measurement reports, etc. from the E2 nodes and O-RUs (via the E2 nodes forwarded by the SMO) for purposes of training and execution of associated AI / ML models (e.g., EE / ES AI / ML models) (e.g., which may comprise R1 / O1 consumer and / or production services).

[0101] Additionally, one or more rApps hosted by the NRT-RIC are configured to infer an O1 configuration optimized for EE / ES through the R1 / O1 interface (e.g., may comprise R1 / O1 consumer and / or production services).

[0102] In one embodiment, the rApp may be configured to retrain, update, and configure the EE / ES AI / ML models.

[0103] For this purpose, one or more E2 nodes (i.e., O-DU, O-CU, etc.) in Figure 1 are configured to report, for example, cell configurations, performance indicators, measurement reports (e.g., cell load related information, traffic information, EE / EC measurement reports, etc.) to the SMO via the O1 interface. SMO framework functions such as O1 termination enable the SMO to communicate with the E2 nodes.

[0104] Additionally, one or more E2 nodes (i.e., O-DU, O-CU, etc.) in FIG. 1 may be configured to perform RF channel reconfiguration (e.g., O-RU Tx / Rx array selection, changing the number of SSB beams, changing the O-RU antenna transmit power, changing the number of single-user / multi-user (SU / MU) MIMO data layers or spatial streams) as part of the EE / ES optimization.

[0105] In one embodiment, the O-RU of FIG. 1 is configured to report energy consumption (EC) and energy efficiency (EE) related information (e.g., cell load related information, traffic information, EE / EC measurement reports, etc.) to the E2 node (i.e., O-DU) via an open FH M-Plane interface.

[0106] In one embodiment, one or more O-RUs of FIG. 1 may be configured to report energy consumption (EC) and energy efficiency (EE) related information (e.g., cell load related information, traffic information, EE / EC measurement reports, etc.) directly to the SMO / NRT-RIC.

[0107] Below, decision-making, potentially including training and inference of AI / ML models, is done in the NRT-RIC.

[0108] FIG. 5 is a flow diagram of a method for implementing optimization of RF channel reconfiguration in m-MIMO antennas in an O-RU according to one embodiment.

[0109] 5, a method for optimizing RF channel reconfiguration in an m-MIMO antenna in an O-RU is implemented by a service management and orchestration (SMO) framework comprising a non-real-time RAN intelligent controller (NRT-RIC), an NRT-RIC framework, at least one SMO function (e.g., O1 termination), and an rApp hosted by the NRT-RIC. The SMO framework may act as an intermediary between the rApp and the E2 node and the O-RU (via the E2 node) within the O-RAN.

[0110] In step 501, the rApp collects O1-related data from the E2 node (i.e., O-CU, O-DU, etc.) via the R1 interface through the NRT-RIC framework and via the O1 interface through the SMO function in the SMO framework (i.e., the SMO function configured in the SMO as the O1 termination of the O1 interface), providing the O1 configuration required to perform RF channel reconfiguration. The O1-related data is collected via the open fronthaul management plane (FH M-Plane) interface between the E2 node and the open radio unit (O-RU).

[0111] In one embodiment, collecting O1-related data that provides the O1 configuration necessary to perform RF channel reconfiguration may include sending, by the rApp, an O1-related data collection request to the E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface (i.e., O1 termination) through an SMO function within the SMO framework. The E2 node may receive the O1-related data collection request from the SMO function and may collect O1-related data that provides the O1 configuration necessary to perform RF channel reconfiguration from the O-RU via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU.

[0112] In one embodiment, for collecting O1-related data that provides the O1 configuration necessary to perform RF channel reconfiguration, the E2 node may activate a measurement report (i.e., an EE / EC measurement report) to the O-RU, and the O-RU provides measurement data (i.e., input data) for the measurement report.

[0113] Upon collecting O1-related data from the O-RU, the E2 node may send the O1-related data to the rApp via the R1 interface, providing the O1 configuration necessary to perform the RF channel reconfiguration collected via the O1 interface through the SMO function in the SMO framework and the NRT-RIC framework.

[0114] In step 502, the SMO retrains at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data, and deploys and activates, via an rApp, one of the at least one retrained AI / ML models to infer data that provides the O1 configuration required to perform RF channel reconfiguration within the O-RAN.

[0115] In one embodiment, O1-related data that provides the O1 configuration necessary to perform RF channel reconfiguration may be input data (e.g., measurement data) used in training and inference of an AI / ML model.

[0116] The O1-related data (i.e., input data) providing the O1 configuration required to perform RF channel reconfiguration may include, in addition to other O1-related data, the following measurement data for monitoring the energy consumption and energy efficiency (EC / EE) of one or more E2 nodes and one or more O-RUs: downlink Packet Data Convergence Protocol Service Data Unit (DL PDCP SDU) data volume (data volume in DL delivered from O-CU-UP to O-DU) per interface, per public land mobile network (PLMN), per quality of service (QoS) level, per slice, per F1-U interface, Xn-U interface, and X2-U interface; uplink Packet Data Convergence Protocol Service Data Unit (UP PDCP SDU) data volume (data volume in DL delivered from O-CU-UP to O-DU) per interface, per public land mobile network (PLMN), per quality of service (QoS) level, per slice, per F1-U interface, Xn-U interface, and X2-U interface; SDU) data volume (data volume in the UL delivered from O-CU-UP to O-DU), Reference Signal Received Quality (RSRQ) measurements per cell per Synchronization Signal Block (SSB), Reference Signal Received Power (RSRP) measurements per cell per SSB, Signal-to-Interference-plus-Noise Ratio (SINR) measurements per cell per SSB, energy consumption, power consumed by hardware components, transmit power, per-cell and per-carrier load statistics (number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, Downlink / Uplink (DL / UL) cell / user throughput, Precoding Matrix Indicator / Channel State Information (PMI / CSI) reports, latency statistics per cell (e.g., when Ultra Reliable Low Latency Communications (URLLC) slices are involved, latency is used to define Energy Efficiency (EE)), and power consumption (i.e., the specific EEPower consumption metrics (i.e., average total / per carrier power consumption, average total / per carrier transmit power) information on supported Tx / Rx array selections along with required site / O-RU input power for KPIs (KPIs).

[0117] In one embodiment, the NRT-RIC framework may retrain at least one AI / ML model. According to this embodiment, an rApp selects an AI / ML model from multiple AI / ML models and sends an initiation request to the NRT-RIC framework to retrain the AI / ML model. The NRT-RIC framework retrains the AI / ML model. In doing so, the rApp monitors the retrained AI / ML model parameters and determines, based on the retrained AI / ML model parameters, to retrieve the retrained AI / ML model from the NRT-RIC framework. Based on the retrieval decision, the rApp requests the retrained AI / ML model from the NRT-RIC framework. Upon receiving the request, the NRT-RIC framework sends the retrained AI / ML model to the rApp.

[0118] In another embodiment, an rApp hosts multiple AI / ML models and retrains one of the AI / ML models.

[0119] Still referring to FIG. 5, in step 503, the rApp monitors O1-related data via the R1 interface through the NRT-RIC framework and via the O1 interface through the SMO function in the SMO framework to provide the O1 configuration necessary to perform RF channel reconfiguration.

[0120] In one embodiment, the rApp may constantly monitor, for example, the performance and energy consumption of the E2 node and the energy consumption of the O-RU.

[0121] Furthermore, in one embodiment, the rApp monitors performance and energy consumption parameters for evaluation of the O1 configuration required to perform RF channel reconfiguration. These performance and energy consumption parameters may include configurations, performance indicators, measurement reports (e.g., cell load related information, traffic information, EE / EC measurement reports, etc.).

[0122] For example, the O1-related data (i.e., input data) providing the O1 configuration required to perform RF channel reconfiguration may include at least one of a configuration, a performance indicator, and a measurement report provided from the O-RU. The measurement report may include at least one of cell load-related information, a measurement report, a traffic information measurement report, and an energy efficiency / energy consumption (EE / EC) measurement report. The energy efficiency / energy consumption (EE / EC) measurement report may include at least one of energy consumption of the E2 node, energy consumption of the O-RU, and one or more performance-related KPIs of the E2 node.

[0123] In step 504, the rApp evaluates O1-related data that provides the O1 configuration required to perform RF channel reconfiguration and determines to generate O1 configuration data for preparing and performing RF channel reconfiguration.

[0124] Further, in step 504, when the rApp generates O1 configuration data for preparing and performing RF channel reconfiguration, it sends the O1 configuration data for preparing and performing RF channel reconfiguration to the E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through the SMO function.

[0125] In one embodiment, based on O1-related data (i.e., input data) that provides the O1 configuration required to perform RF channel reconfiguration, if a predetermined performance target (e.g., EE / ES performance target) is not achieved, the rApp determines to generate O1 configuration data (i.e., output data) for preparing and performing RF channel reconfiguration. In this case, the rApp generates O1 configuration data for preparing and performing RF channel reconfiguration.

[0126] For example, the EE / ES performance target may be an A1 policy in the NRT-RIC or may be based on targets set by the network operator for energy saving (ES) functions in the NRT-RIC (i.e., predetermined performance parameters for EE / ES in the O-RAN, e.g., one or more predetermined performance targets for EE / EC in the O-RAN).

[0127] In one embodiment, the O1 configuration data (i.e., output data) for preparing and performing the generated RF channel reconfiguration may include, for example, an NRCellCU Information Object Class IOC, an NRCellDU IOC, a GNBDUFunction IOC, a GNBCUCPFunction IOC, a GNBCUUPFunction IOC, etc., as defined in 3GPP TS 28.541: “3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Management and orchestration; 5G Network Resource Model (NRM); Stage 2 and stage 3”, Release 16, December 2020, to enable energy-saving RF channel reconfiguration.

[0128] For example, RF channel reconfiguration may include O-RU Tx / Rx array selection, changing the number of SU / MU MIMO spatial streams or data layers, changing the number of SSB beams, changing the antenna transmit power of the O-RU, etc.

[0129] In step 505, when the E2 node receives the O1 configuration data for preparing and performing RF channel reconfiguration, the E2 node converts the O1 configuration data for preparing and performing RF channel reconfiguration and instructs the O-RU to perform RF channel reconfiguration via the open FH M-Plane.

[0130] In one embodiment, implementing the O1 configuration data to prepare and perform the RF channel reconfiguration may further include the O-RU notifying the E2 node of completion of implementing the RF channel reconfiguration.

[0131] Upon receiving the notification from the O-RU, the E2 node notifies the rApp via the O1 interface through the SMO function and via the R1 interface through the NRT-RIC framework. According to an embodiment, the O-RU may notify the E2 node via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU.

[0132] In further embodiments, after implementation in step 505, the NRT-RIC may monitor the performance of the retrained AI / ML model and may determine that predetermined performance goals are not being achieved, in which case the NRT-RIC may initiate a fallback mechanism and / or initiate an update or retraining of the AI / ML model.

[0133] 6 illustrates a data collection flow according to one embodiment. Referring to FIG. 6, data collection is aimed at enabling RF channels through RF channel reconfiguration parameter changes (i.e., implementation of O1 configuration data to prepare and execute RF channel reconfiguration) and actions that enable AI / ML-based solutions to optimize RF channels for EE / ES in O-RAN controlled by the NRT-RIC.

[0134] To this end, the SMO function may be the O1 termination point for the O1 interface. The non-RT-RIC framework and / or rApp may perform AI / ML-based optimization of RF channel reconfiguration. At least one O-RAN E2 node and O-RU may enable (i.e., implement) an optimized configuration for RF channel reconfiguration.

[0135] Referring to Figure 6, once the R1 interface and O1 interface connections and the open FH M-Plane interface between the E2 node and the O-RU are established, a communication path between the rApp and the E2 node and the O-RU is established within the O-RAN.

[0136] According to the O-RAN system architecture, the NRT-RIC has knowledge of overlapping carriers / cells and the coverage of those carriers / cells (e.g., which carriers / cells are coverage layers and which are capacity layers).

[0137] To optimize EE / ES in the O-RAN, a network operator may set targets (i.e., predetermined performance parameters for EE / ES in the O-RAN, e.g., one or more predetermined performance goals for EE / EC in the O-RAN) for the energy saving (ES) function in the NRT-RIC. The targets may include an ES target that reduces the power consumption of the O-RU by switching off, for example, 56, 48, 32, 16, 8, etc., of the 64 Tx / Rx arrays of the O-RU in the digital m-MIMO architecture and reducing the number of corresponding spatial layers and synchronization signal blocks (SSBs).

[0138] As a result, the method for optimizing RF channel reconfiguration may begin when the network operator activates the optimization rApp along with the initial AI / ML model for the RF channel reconfiguration ES function and the E2 nodes and O-RUs are operational.

[0139] In operation 1, the rApp requests the NRT-RIC framework to collect O1 related data such as required configuration, performance indicators, measurement data (i.e., input data) via the R1 interface.

[0140] In operation 2, the NRT-RIC framework requests the SMO framework to collect O1 related data (ie, input data) from the E2 node.

[0141] In operation 3, the SMO framework function (i.e., the SMO function) requests data collection from the E2 node and the O-RU (via the E2 node).

[0142] In operation 4, upon receiving a request from the SMO, one or more E2 nodes (i.e., O-CU, O-DU, etc.) request and collect O1-related data (i.e., input data) from the O-RU via the open FH M-Plane interface.

[0143] In operation 5, one or more E2 nodes (ie, O-CU, O-DU, etc.) periodically and / or event-based send O1-related data (ie, input data) to the SMO.

[0144] In operation 6, the NRT-RIC collects O1 related data (ie, input data) (eg, for consuming and / or producing R1 services related to EE / ES).

[0145] In operation 7, the rApp collects O1 related data (i.e., input data) for processing (e.g., for consuming and / or producing R1 services related to EE / ES).

[0146] FIG. 7 illustrates a data analysis, AI / ML model training, and inference flow according to one embodiment. Referring to FIG. 7 , in operation 8, at least one AI / ML model of the plurality of AI / ML models may be retrained on the NRT-RIC framework or an rApp. In one embodiment, if the NRT-RIC framework is hosting the retraining of at least one AI / ML model of the plurality of AI / ML models, the rApp selects one AI / ML model of the plurality of AI / ML models and initiates retraining of the selected AI / ML model on the Non-RT-RIC framework. In one embodiment, the retraining and selection of the AI / ML model may be performed by an alternative AI / ML workflow within the SMO.

[0147] In operation 9, upon receiving a retraining request from the rApp, the NRT-RIC framework initiates retraining of the AI / ML model.

[0148] In operation 10, the rApp monitors the retrained AI / ML model and retrieves the retrained AI / ML model from the NRT-RIC. In one embodiment, the AI / ML model retrieval procedure on the R1 interface may be performed by an alternative AI / ML workflow in the SMO based on the R1 service.

[0149] In operation 11, upon receiving a retrieval request from the rApp, the NRT-RIC framework forwards the AI / ML model (i.e., the retrained AI / ML model) to the rApp.

[0150] In one embodiment, the AI / ML model transfer procedure on the R1 interface may be performed by an alternative AI / ML workflow within the SMO based on the R1 service.

[0151] In operation 12, if the retraining of the AI / ML model is hosted by an rApp, the AI / ML model is retrained on the rApp itself.

[0152] In operation 13, once the retraining of the AI / ML models has been performed, at least one AI / ML model (including the retrained AI / ML model) is deployed and activated for inference (i.e., for inferring data that provides the O1 configuration necessary to perform RF channel reconfiguration within the O-RAN).

[0153] 8 illustrates a flow of data analysis, AI / ML model training, and inference according to one embodiment. Referring to FIG. 8, data analysis, AI / ML model training, and inference may be performed by an rApp.

[0154] To this end, in operation 12, the retraining of the AI / ML model is hosted by the rApp, and the AI / ML model is retrained on the rApp itself.

[0155] In operation 13 of FIG. 8, once the retraining of the AI / ML models has been performed, at least one AI / ML model (including the retrained AI / ML model) is deployed and activated for inference (i.e., for inferring data that provides the O1 configuration necessary to perform on / off switching of cells and / or carriers within the O-RAN).

[0156] 7 and 8, in operation 13, the rApp constantly monitors the performance and energy consumption of the E2 node, the energy consumption of the O-RU, etc. For example, the rApp monitors the performance and energy consumption for evaluation of the O1 configuration (i.e., input data) required to perform RF channel reconfiguration.

[0157] In one embodiment, the O1-related data (i.e., input data) may be input data used in training and inference of an AI / ML model. The O1-related data may include, in addition to other O1-related data, the following measurement data for monitoring energy consumption and energy efficiency (EC / EE) of one or more E2 nodes and one or more O-RUs: downlink Packet Data Convergence Protocol Service Data Unit (DL PDCP SDU) data volume (data volume in DL delivered from O-CU-UP to O-DU) per interface, per public land mobile network (PLMN), per quality of service (QoS) level, per slice, per F1-U interface, Xn-U interface, and X2-U interface; uplink Packet Data Convergence Protocol Service Data Unit (UP PDCP SDU) data volume (data volume in DL delivered from O-CU-UP to O-DU) per interface, per public land mobile network (PLMN), per quality of service (QoS) level, per slice, per F1-U interface, Xn-U interface, and X2-U interface; SDU) data volume (data volume in the UL delivered from O-CU-UP to O-DU), Reference Signal Received Quality (RSRQ) measurements per cell per Synchronization Signal Block (SSB), Reference Signal Received Power (RSRP) measurements per cell per SSB, Signal-to-Interference-plus-Noise Ratio (SINR) measurements per cell per SSB, energy consumption, power consumed by hardware components, transmit power, per-cell and per-carrier load statistics (number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, Downlink / Uplink (DL / UL) cell / user throughput, Precoding Matrix Indicator / Channel State Information (PMI / CSI) reports, latency statistics per cell (e.g., when Ultra Reliable Low Latency Communications (URLLC) slices are involved, latency is used to define Energy Efficiency (EE)), and power consumption (i.e., the specific EEPower consumption metrics (i.e., average total / per carrier power consumption, average total / per carrier transmit power) information on supported Tx / Rx array selections along with required site / O-RU input power for KPIs (KPIs).

[0158] FIG. 9 illustrates the generation and implementation of an O1 configuration for preparing and performing RF channel reconfiguration according to one embodiment.

[0159] Referring to FIG. 9, in operation 14, the rApp generates an O1 configuration (i.e., output data) for preparing and performing RF channel reconfiguration and sends the O1 configuration (i.e., output data) to the SMO via the R1 interface through the NRT-RIC framework.

[0160] In one embodiment, the O1 configuration data (i.e., output data) for preparing and performing the generated RF channel reconfiguration may include output data such as NRCellCU Information Object Class IOC, NRCellDU IOC, GNBDUFunction IOC, GNBCUCPFunction IOC, GNBCUUPFunction IOC, etc., as defined in 3GPP TS 28.541: “3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Management and orchestration; 5G Network Resource Model (NRM); Stage 2 and stage 3,” Release 16, December 2020, to enable energy-saving cell and carrier shutdown and reconfigure resources over the O1 interface.

[0161] Furthermore, O1 configuration data (i.e., output data) for preparing and performing RF channel reconfiguration may include output data such as O-RU Tx / Rx array selection, changing the number of SU / MU MIMO spatial streams or data layers, changing the number of SSB beams, changing the antenna transmit power of the O-RU, etc.

[0162] In operation 15, the NRT-RIC requests, via the O1 interface, that the SMO framework function (ie, SMO function) configure the E2 node to prepare and perform RF channel reconfiguration.

[0163] In operation 16, the SMO instructs the E2 node via the O1 interface to execute the request received from the rApp.

[0164] In operation 17, the E2 node informs the O-RU of the updated O-RU configuration (i.e., RF channel reconfiguration) via an open FH M-Plane. In one embodiment, the O-RU may notify the E2 node when it has completed implementing the RF channel reconfiguration.

[0165] In operation 18, the E2 node notifies the SMO once the implementation of the RF channel reconfiguration is complete.

[0166] In operation 19, the SMO framework function (ie, the SMO function) notifies the NRT-RIC framework of the completion of the RF channel reconfiguration.

[0167] In operation 20, the NRT-RIC notifies the rApp of the completion of the RF channel reconfiguration over the R1 interface.

[0168] In operation 21, the NRT-RIC continuously analyzes the performance of the AI / ML model. In one embodiment, if the energy savings goal is not achieved, the NRT-RIC may decide to initiate a fallback mechanism and / or an update or retraining of the AI / ML model.

[0169] In one embodiment, the method for optimizing RF channel reconfiguration may terminate when the E2 node goes out of service or when the operator disables the optimization function or the AI / ML model for saving energy (i.e., the AI / ML model for EE / ES).

[0170] In another embodiment, the rApp maintains closed-loop monitoring of energy saving functions in the E2 node and the O-RU (via the E2 node).

[0171] According to operation 21, the E2 node and O-RU are put into operation using the newly deployed parameters (i.e., O1 configuration data) / model (i.e., retrained AI / ML model) and state (i.e., RF channel reconfiguration on / off state).

[0172] According to an embodiment, a system for implementing radio frequency (RF) reconfiguration optimization via a service management and orchestration (SMO) framework within an open radio access network (O-RAN) is provided. The system includes a memory storing instructions and at least one processor configured to implement a non-real-time RAN intelligent controller (NRT-RIC), an NRT-RIC framework, at least one SMO function, and an rApp hosted by the NRT-RIC.The at least one processor, via an rApp, collects O1-related data from the E2 node via an R1 interface through the NRT-RIC framework and via an SMO function within the SMO framework, the O1-related data providing an O1 configuration required to perform RF channel reconfiguration, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the open radio unit (O-RU); retrains, via the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; and deploys and activates, via the rApp, one retrained AI / ML model from the at least one retrained AI / ML to infer data providing an O1 configuration required to perform RF channel reconfiguration within the O-RAN; and deploys, via the rApp, one retrained AI / ML model from the at least one retrained AI / ML to infer data providing an O1 configuration required to perform RF channel reconfiguration within the O-RAN. and executing instructions to: monitor, via an rApp, O1-related data that provides an O1 configuration required to perform RF channel reconfiguration via an O1 interface through the NRT-RIC framework; evaluate, via the rApp, the O1-related data that provides the O1 configuration required to perform RF channel reconfiguration; determine, via the rApp, to generate O1 configuration data for preparing and performing RF channel reconfiguration; send, via the rApp, the O1 configuration data for preparing and performing RF channel reconfiguration to at least one E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through at least one SMO function in the SMO framework; and implement, by the E2 node and the O-RU, RF channel reconfiguration in the O-RAN. The at least one processor is further configured, during implementation, to convert, by the E2 node, the O1 configuration data for preparing and performing RF channel reconfiguration, and instruct, by the E2 node, via an open FH M-Plane, the O1 configuration data to the O-RU to perform RF channel reconfiguration.

[0173] The at least one processor may be further configured to, during retraining of the at least one AI / ML model, select, by the rApp, an AI / ML model from the plurality of AI / ML models; send, by the rApp, an initiation request to retrain the AI / ML model to the NRT-RIC framework; retrain, by the NRT-RIC framework, the AI / ML model; monitor, by the rApp, the retrained AI / ML model parameters; determine, based on the retrained AI / ML model parameters, to retrieve the retrained AI / ML model from the NRT-RIC framework; request, by the rApp, the retrained AI / ML model from the NRT-RIC framework; and send, by the NRT-RIC framework, the retrained AI / ML model to the rApp.

[0174] The at least one processor may be further configured to, during retraining of the at least one AI / ML model, retrain one AI / ML model from the plurality of AI / ML models by the rApp.

[0175] The O1-related data providing the O1 configuration necessary to perform RF channel reconfiguration may include at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU. The measurement report may include at least one of an energy efficiency / energy consumption (EE / EC) measurement report. The energy efficiency / energy consumption (EE / EC) measurement report may include at least one of Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell, Reference Signal Received Power (RSRP) measurements per SSB per cell, Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell, energy consumption, power consumed by hardware components, transmit power, per-cell and per-carrier load statistics (such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, Precoding Matrix Indicator / Channel State Information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs).

[0176] The at least one processor may be configured to: during collection of O1-related data that provides the O1 configuration required to perform RF channel reconfiguration, send, by the rApp, an O1-related data collection request to the E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through an SMO function in the SMO framework; receive, by the E2 node, the O1-related data collection request from the SMO function; collect, by the E2 node, O1-related data that provides the O1 configuration required to perform RF channel reconfiguration from the O-RU via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU; and send, by the E2 node, the O1-related data that provides the O1 configuration required to perform RF channel reconfiguration that has been collected via the O1 interface through the SMO function in the SMO framework and the NRT-RIC framework to the rApp via the R1 interface.

[0177] The O1 configuration data for preparing and performing RF channel reconfiguration may include at least one of O-RU Tx / Rx array selection, changing the number of SU / MU MIMO spatial streams or data layers, changing the number of SSB beams, and changing the O-RU antenna transmit power.

[0178] The at least one processor may be further configured to monitor, by the NRT-RIC, the performance of the retrained AI / ML model, determine that predetermined performance goals are not achieved based on the collected O1-related data, and initiate a fallback mechanism and / or an update or retraining of the AI / ML model.

[0179] According to an embodiment, a method for implementing radio frequency (RF) reconfiguration optimization via a service management and orchestration (SMO) framework within an open radio access network (O-RAN) is provided. The method includes: collecting, by an rApp, O1-related data from an E2 node via an R1 interface through an NRT-RIC framework and via an SMO function within the SMO framework, the O1-related data providing an O1 configuration required to perform RF channel reconfiguration, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between an E2 node and an open radio unit (O-RU); retraining, by the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; deploying and activating, by the rApp, one of the at least one retrained AI / ML model for inferring data providing an O1 configuration required to perform RF channel reconfiguration within the O-RAN; and transmitting, by the rApp, O1-related data via the R1 interface through the NRT-RIC framework and via an SMO function within the SMO framework. monitoring, via an MO function, via an O1 interface, O1-related data that provides the O1 configuration required to perform RF channel reconfiguration; evaluating, via the rApp, the O1-related data that provides the O1 configuration required to perform RF channel reconfiguration; determining, via the rApp, to generate O1 configuration data for preparing and performing RF channel reconfiguration; sending, via the rApp, the O1 configuration data for preparing and performing RF channel reconfiguration to at least one E2 node via an R1 interface through an NRT-RIC framework and via an O1 interface through at least one SMO function in an SMO framework; and implementing, by the E2 node and the O-RU, the RF channel reconfiguration in the O-RAN.The implementing includes: converting, by the E2 node, O1 configuration data for preparing and performing RF channel reconfiguration; and instructing, by the E2 node, via an open FH M-Plane, the O-RU to perform RF channel reconfiguration.

[0180] Retraining at least one AI / ML model includes selecting, by the rApp, an AI / ML model from the plurality of AI / ML models; sending, by the rApp, an initiation request to retrain the AI / ML model to the NRT-RIC framework; retraining, by the NRT-RIC framework, the AI / ML model; monitoring, by the rApp, retrained AI / ML model parameters and determining, based on the retrained AI / ML model parameters, to retrieve the retrained AI / ML model from the NRT-RIC framework; requesting, by the rApp, the retrained AI / ML model from the NRT-RIC framework; and sending, by the NRT-RIC framework, the retrained AI / ML model to the rApp.

[0181] Retraining at least one AI / ML model includes retraining one AI / ML model from the plurality of AI / ML models by the rApp.

[0182] The O1-related data providing the O1 configuration necessary to perform RF channel reconfiguration may include at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU. The measurement report may include at least one of an energy efficiency / energy consumption (EE / EC) measurement report. The energy efficiency / energy consumption (EE / EC) measurement report may include at least one of Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell, Reference Signal Received Power (RSRP) measurements per SSB per cell, Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell, energy consumption, power consumed by hardware components, transmit power, per-cell and per-carrier load statistics (such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, Precoding Matrix Indicator / Channel State Information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs).

[0183] Collecting O1-related data that provides an O1 configuration necessary to perform RF channel reconfiguration includes sending, by the rApp, an O1-related data collection request to the E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through an SMO function in the SMO framework; receiving, by the E2 node, the O1-related data collection request from the SMO function; collecting, by the E2 node, O1-related data from an open radio unit (O-RU) via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU that provides the O1 configuration necessary to perform RF channel reconfiguration; and sending, by the E2 node, the O1-related data that provides the O1 configuration necessary to perform RF channel reconfiguration that has been collected via the O1 interface through the SMO function in the SMO framework and the NRT-RIC framework to the rApp via the R1 interface.

[0184] The O1 configuration data for preparing and performing RF channel reconfiguration may include at least one of O-RU Tx / Rx array selection, changing the number of SU / MU MIMO spatial streams or data layers, changing the number of SSB beams, and changing the O-RU antenna transmit power.

[0185] The method may further include monitoring, by the NRT-RIC, performance of the retrained AI / ML model, determining that predetermined performance goals are not achieved based on the collected O1-related data, and initiating a fallback mechanism and / or updating or retraining the AI / ML model.

[0186] According to an embodiment, there is provided a non-transitory computer-readable storage medium having stored thereon instructions executable by at least one processor configured to implement a Non-Real-Time RAN Intelligent Controller (NRT-RIC), an NRT-RIC framework, at least one SMO function, and an rApp hosted by the NRT-RIC to perform a method for implementing optimization of radio frequency (RF) reconfiguration via a service management and orchestration (SMO) framework within an Open Radio Access Network (O-RAN).The method includes: collecting, by an rApp, O1-related data from an E2 node via an R1 interface through an NRT-RIC framework and via an O1 interface through an SMO function within an SMO framework, the O1-related data providing an O1 configuration required to perform RF channel reconfiguration, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between an E2 node and an open radio unit (O-RU); retraining, by the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; deploying and activating, by the rApp, one retrained AI / ML model from the at least one retrained AI / ML to infer data providing an O1 configuration required to perform RF channel reconfiguration within the O-RAN; and transmitting, by the rApp, O1-related data from the E2 node via an R1 interface through the NRT-RIC framework and via an SMO function within the SMO framework. and implementing, by the E2 node and the O-RU, the RF channel reconfiguration in the O-RAN. The implementing includes converting, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration, and instructing, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration. The O1 configuration data includes converting, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration, and instructing, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration via an open FH M-Plane.

[0187] Retraining at least one AI / ML model includes selecting, by the rApp, an AI / ML model from the plurality of AI / ML models; sending, by the rApp, an initiation request to retrain the AI / ML model to the NRT-RIC framework; retraining, by the NRT-RIC framework, the AI / ML model; monitoring, by the rApp, retrained AI / ML model parameters and determining, based on the retrained AI / ML model parameters, to retrieve the retrained AI / ML model from the NRT-RIC framework; requesting, by the rApp, the retrained AI / ML model from the NRT-RIC framework; and sending, by the NRT-RIC framework, the retrained AI / ML model to the rApp.

[0188] Retraining at least one AI / ML model includes retraining one AI / ML model from the plurality of AI / ML models by the rApp.

[0189] The O1-related data providing the O1 configuration necessary to perform RF channel reconfiguration may include at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU. The measurement report may include at least one of an energy efficiency / energy consumption (EE / EC) measurement report. The energy efficiency / energy consumption (EE / EC) measurement report may include at least one of Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell, Reference Signal Received Power (RSRP) measurements per SSB per cell, Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell, energy consumption, power consumed by hardware components, transmit power, per-cell and per-carrier load statistics (such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, Precoding Matrix Indicator / Channel State Information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs).

[0190] Collecting O1-related data that provides an O1 configuration necessary to perform RF channel reconfiguration includes sending, by the rApp, an O1-related data collection request to the E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through an SMO function in the SMO framework; receiving, by the E2 node, the O1-related data collection request from the SMO function; collecting, by the E2 node, O1-related data from an open radio unit (O-RU) via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU that provides the O1 configuration necessary to perform RF channel reconfiguration; and sending, by the E2 node, the O1-related data that provides the O1 configuration necessary to perform RF channel reconfiguration that has been collected via the O1 interface through the SMO function in the SMO framework and the NRT-RIC framework to the rApp via the R1 interface.

[0191] The O1 configuration data for preparing and performing RF channel reconfiguration may include at least one of O-RU Tx / Rx array selection, changing the number of SU / MU MIMO spatial streams or data layers, changing the number of SSB beams, and changing the O-RU antenna transmit power.

[0192] The method may further include monitoring, by the NRT-RIC, performance of the retrained AI / ML model, determining that predetermined performance goals are not achieved based on the collected O1-related data, and initiating a fallback mechanism and / or updating or retraining the AI / ML model.

[0193] According to an embodiment, the system and method enable energy savings (ES) by reducing the power consumption of an O-RU through RF channel reconfiguration (e.g., by switching off specific transmitter / receiver (Tx / Rx) arrays). For example, ES can be achieved by switching off 32 of the 64 Tx / Rx arrays of an O-RU in a digital m-MIMO architecture and reducing the number of corresponding spatial layers and synchronization signal blocks (SSBs).

[0194] As a result, the system and method implement an NRT-RIC framework that allows network operators to flexibly configure RF channel reconfiguration (e.g., switching on / off Tx / Rx arrays in m-MIMO antennas in O-RUs) to optimize energy efficiency across the network, instead of local optimization in the O-RAN.

[0195] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit implementations to the precise form disclosed. Modifications and variations are possible in light of the foregoing disclosure or may be acquired from practice of the implementations.

[0196] Some embodiments may relate to systems, methods, and / or computer-readable media at any possible level of technical detail of integration. Furthermore, one or more of the above-described components may be implemented as instructions stored on a computer-readable medium and executable by at least one processor (and / or may include at least one processor). The computer-readable medium may include a computer-readable non-transitory storage medium (or medium) having computer-readable program instructions stored thereon for causing a processor to perform operations.

[0197] A computer-readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically encoded devices such as punch cards or raised structures in grooves in which instructions are recorded, and any suitable combination thereof. As used herein, computer-readable storage medium is not to be understood as a transitory signal per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or electrical signals transmitted over wires.

[0198] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium into each computing / processing device, or may be downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and transfers the computer-readable program instructions for storage in a computer-readable storage medium within the respective computing / processing device.

[0199] The computer-readable program code / instructions for carrying out operations may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for an integrated circuit, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and procedural programming languages ​​such as the "C" programming language, or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server, as a standalone software package. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be to an external computer (e.g., through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA) may execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuitry to perform a certain aspect or operation.

[0200] These computer-readable program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce an apparatus, such that the instructions, when executed by the processor of the computer or other programmable data processing apparatus, produce means for implementing the functions / acts set forth in the flowcharts and / or block diagrams (one or more blocks). These computer-readable program instructions may be stored on a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and / or other device to function in a particular manner, such that the computer-readable storage medium on which the instructions are stored comprises an article including instructions that implement aspects of the functions / acts set forth in the flowcharts and / or block diagrams (one or more blocks).

[0201] The computer-readable program instructions may be loaded onto a computer, other programmable data processing apparatus, or other device such that a series of operational steps are performed on the computer, other programmable apparatus, or other device to generate a computer-implemented process such that the instructions, executing on the computer, other programmable apparatus, or other device, implement the functions / acts described in the flowcharts and / or block diagrams (one or more blocks).

[0202] The illustrated flowcharts and block diagrams illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer-readable media according to various embodiments. Each block in a flowchart or block diagram may represent a microservice, module, segment, or portion of instructions, comprising one or more executable instructions for implementing specific logical functions. The methods, computer systems, and computer-readable media may include additional, fewer, different, or differently arranged blocks than those shown in the figures. In some alternative implementations, the functions shown in the blocks may occur out of the order shown in the figures. For example, two blocks shown in succession may actually be executed concurrently or substantially concurrently, depending on the functionality involved, or the blocks may be executed in the reverse order. Note that each block of the block diagram and / or flowchart illustrations, and combinations of blocks in the block diagram and / or flowchart illustrations, may be implemented by a dedicated hardware-based system that performs specific functions or acts, or by executing a combination of dedicated hardware and computer instructions.

[0203] It will be apparent that the systems and / or methods described herein may be implemented in different forms, such as hardware, firmware, or a combination of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit the implementation. As such, the operation and behavior of the systems and / or methods are described herein without reference to specific software code. It will be understood that software and hardware may be designed to implement the systems and / or methods based on the description herein.

Claims

1. 1. A system for implementing radio frequency (RF) reconfiguration optimization via a service management and orchestration (SMO) framework within an open radio access network (O-RAN), comprising: a memory for storing instructions; at least one processor configured to implement a Non-Real-Time RAN Intelligent Controller (NRT-RIC), an NRT-RIC framework, at least one SMO function, and an rApp hosted by the NRT-RIC; Equipped with The at least one processor: collecting, by an rApp, O1-related data from an E2 node via an R1 interface through an NRT-RIC framework and via an O1 interface through an SMO function within the SMO framework, the O1-related data providing the O1 configuration required to perform the RF channel reconfiguration, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between the E2 node and an open radio unit (O-RU); retraining, by the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; deploying and activating, by the rApp, one of the at least one retrained AI / ML models to infer data providing an O1 configuration necessary to perform the RF channel reconfiguration within the O-RAN; monitoring, by the rApp, the O1-related data that provides the O1 configuration necessary to perform the RF channel reconfiguration via the R1 interface through the NRT-RIC framework and via the O1 interface through the SMO function within the SMO framework; evaluating, by the rApp, the O1-related data that provides the O1 configuration necessary to perform the RF channel reconfiguration; determining, by the rApp, to generate O1 configuration data for preparing and performing the RF channel reconfiguration; sending, by the rApp, the O1 configuration data for preparing and performing the RF channel reconfiguration to the at least one E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through the at least one SMO function within the SMO framework; Implementing the RF channel reconfiguration within the O-RAN by the E2 node and the O-RU. configured to execute the instructions to The at least one processor, during implementation, translating, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration; instructing the O-RU to perform the RF channel reconfiguration via the open FH M-Plane by the E2 node; The system further comprises:

2. The at least one processor, during retraining of the at least one AI / ML model, The rApp selects one AI / ML model from multiple AI / ML models, sending, by the rApp, an initiation request to the NRT-RIC framework to retrain the AI / ML model; retraining the AI / ML model with the NRT-RIC framework; monitoring, by the rApp, retrained AI / ML model parameters and determining, based on the retrained AI / ML model parameters, the withdrawal of the retrained AI / ML model from the NRT-RIC framework; requesting the retrained AI / ML model from the NRT-RIC framework by the rApp; Sending the retrained AI / ML model to the rApp via the NRT-RIC framework; The system of claim 1 further configured to:

3. 2. The system of claim 1, wherein the at least one processor is further configured to, during retraining of at least one AI / ML model, retrain one AI / ML model from the plurality of AI / ML models by the rApp.

4. the O1-related data providing the O1 configuration necessary to perform the RF channel reconfiguration comprises at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU; the measurement report comprises at least one energy efficiency / energy consumption (EE / EC) measurement report; the energy efficiency / energy consumption (EE / EC) measurement report comprises at least one of: Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell; Reference Signal Received Power (RSRP) measurements per SSB per cell; Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell; energy consumption; power consumed by hardware components; transmit power; per-cell and per-carrier load statistics, such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, precoding matrix indicator / channel state information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs); The system of claim 1 .

5. The at least one processor, during collection of the O1-related data that provides the O1 configuration necessary to perform the RF channel reconfiguration, sending, by the rApp, an O1-related data collection request to the E2 node via an R1 interface through the NRT-RIC framework and via an O1 interface through the SMO function in the SMO framework; receiving, by the E2 node, the O1-related data collection request from the SMO function; collecting, by the E2 node, from the open radio unit (O-RU) via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU, the O1-related data providing an O1 configuration necessary to perform the RF channel reconfiguration; sending, by the E2 node, to the rApp via the R1 interface, the O1-related data providing the O1 configuration necessary to perform the RF channel reconfiguration collected via the O1 interface through the SMO function within the SMO framework and the NRT-RIC framework; The system of claim 1 configured to:

6. 2. The system of claim 1, wherein the O1 configuration data for preparing and performing the RF channel reconfiguration comprises at least one of an O-RU Tx / Rx array selection, a change in the number of SU / MU MIMO spatial streams or data layers, a change in the number of SSB beams, and a change in the antenna transmit power of the O-RU.

7. The at least one processor: monitoring the performance of the retrained AI / ML model by the NRT-RIC; determining that predetermined performance goals will not be achieved based on the collected O1-related data; Initiating fallback mechanisms and / or updating or retraining AI / ML models; The system of claim 1 further configured to:

8. 1. A method for implementing radio frequency (RF) reconfiguration optimization via a service management and orchestration (SMO) framework in an open radio access network (O-RAN), comprising: collecting, by an rApp, O1-related data that provides an O1 configuration required to perform the RF channel reconfiguration from an E2 node via an R1 interface through an NRT-RIC framework and via an O1 interface through an SMO function within the SMO framework, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between the E2 node and an open radio unit (O-RU); retraining, by the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; deploying and activating, by the rApp, one of the at least one retrained AI / ML models to infer data providing an O1 configuration necessary to perform the RF channel reconfiguration within the O-RAN; monitoring, by the rApp, the O1-related data through the NRT-RIC framework via the R1 interface and through the SMO function in the SMO framework via an O1 interface, to provide the O1 configuration necessary to perform the RF channel reconfiguration; evaluating, by the rApp, the O1-related data that provides the O1 configuration necessary to perform the RF channel reconfiguration; determining, by the rApp, to generate O1 configuration data for preparing and performing the RF channel reconfiguration; sending, by the rApp, the O1 configuration data for preparing and performing the RF channel reconfiguration to the at least one E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through the at least one SMO function within the SMO framework; Implementing, by the E2 node and the O-RU, the RF channel reconfiguration in the O-RAN; Equipped with The implementation comprises: converting, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration; instructing, by the E2 node, the O-RU to perform the RF channel reconfiguration via the open FH M-Plane; A method for providing the above.

9. retraining the at least one AI / ML model selecting, by the rApp, one AI / ML model from a plurality of AI / ML models; sending, by the rApp, an initiation request to retrain the AI / ML model to the NRT-RIC framework; retraining the AI / ML model with the NRT-RIC framework; monitoring, by the rApp, retrained AI / ML model parameters and determining, based on the retrained AI / ML model parameters, the withdrawal of the retrained AI / ML model from the NRT-RIC framework; requesting the retrained AI / ML model from the NRT-RIC framework by the rApp; Sending the retrained AI / ML model to the rApp via the NRT-RIC framework; The method of claim 8 comprising:

10. 9. The method of claim 8, wherein retraining the at least one AI / ML model comprises retraining, by the rApp, one AI / ML model from the plurality of AI / ML models.

11. the O1-related data providing the O1 configuration necessary to perform the RF channel reconfiguration comprises at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU; the measurement report comprises at least one energy efficiency / energy consumption (EE / EC) measurement report; the energy efficiency / energy consumption (EE / EC) measurement report comprises at least one of: Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell; Reference Signal Received Power (RSRP) measurements per SSB per cell; Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell; energy consumption; power consumed by hardware components; transmit power; per-cell and per-carrier load statistics, such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, precoding matrix indicator / channel state information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs); The method of claim 8.

12. collecting the O1-related data that provides an O1 configuration necessary to perform the RF channel reconfiguration includes: sending, by the rApp, an O1-related data collection request to the E2 node via an R1 interface through the NRT-RIC framework and via an O1 interface through the SMO function in the SMO framework; receiving, by the E2 node, the O1-related data collection request from the SMO function; collecting, by the E2 node, from the open radio unit (O-RU) via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU, the O1-related data providing an O1 configuration required to perform the RF channel reconfiguration; sending, by the E2 node, the O1-related data to the rApp via the R1 interface, providing the O1 configuration necessary to perform the SMO function within the SMO framework and the RF channel reconfiguration collected via the O1 interface through the NRT-RIC framework; The method of claim 8 comprising:

13. 10. The method of claim 8, wherein the O1 configuration data for preparing and performing the RF channel reconfiguration comprises at least one of an O-RU Tx / Rx array selection, a change in the number of SU / MU MIMO spatial streams or data layers, a change in the number of SSB beams, and a change in the antenna transmit power of the O-RU.

14. monitoring the performance of the retrained AI / ML model by the NRT-RIC; determining that predetermined performance goals will not be achieved based on the collected O1-related data; and Initiating fallback mechanisms and / or updating or retraining AI / ML models; and The method of claim 8 further comprising:

15. 1. A non-transitory computer-readable storage medium having stored thereon instructions executable by at least one processor configured to implement a Non-Real-Time RAN Intelligent Controller (NRT-RIC), an NRT-RIC framework, at least one SMO function, and an rApp hosted by the NRT-RIC to perform a method for implementing radio frequency (RF) reconfiguration optimization via a service management and orchestration (SMO) framework within an Open Radio Access Network (O-RAN), the non-transitory computer-readable storage medium comprising: The method comprises: collecting, by an rApp, O1-related data that provides an O1 configuration required to perform the RF channel reconfiguration from an E2 node via an R1 interface through an NRT-RIC framework and via an O1 interface through an SMO function within the SMO framework, the O1-related data being collected via an open fronthaul management plane (FH M-Plane) interface between the E2 node and an open radio unit (O-RU); retraining, by the SMO, at least one artificial intelligence / machine learning (AI / ML) model based on the collected O1-related data; deploying and activating, by the rApp, one of the at least one retrained AI / ML models to infer data providing an O1 configuration necessary to perform the RF channel reconfiguration within the O-RAN; monitoring, by the rApp, the O1-related data through the NRT-RIC framework via the R1 interface and through the SMO function in the SMO framework via an O1 interface, to provide the O1 configuration necessary to perform the RF channel reconfiguration; evaluating, by the rApp, the O1-related data that provides the O1 configuration necessary to perform the RF channel reconfiguration; determining, by the rApp, to generate O1 configuration data for preparing and performing the RF channel reconfiguration; sending, by the rApp, the O1 configuration data for preparing and performing the RF channel reconfiguration to the at least one E2 node via the R1 interface through the NRT-RIC framework and via the O1 interface through the at least one SMO function within the SMO framework; Implementing, by the E2 node and the O-RU, the RF channel reconfiguration in the O-RAN; Equipped with The implementation comprises: converting, by the E2 node, the O1 configuration data for preparing and performing the RF channel reconfiguration; instructing, by the E2 node, the O-RU to perform the RF channel reconfiguration via the open FH M-Plane; A non-transitory computer-readable recording medium comprising:

16. retraining the at least one AI / ML model selecting, by the rApp, one AI / ML model from a plurality of AI / ML models; sending, by the rApp, an initiation request to retrain the AI / ML model to the NRT-RIC framework; retraining the AI / ML model with the NRT-RIC framework; monitoring, by the rApp, retrained AI / ML model parameters and determining, based on the retrained AI / ML model parameters, the withdrawal of the retrained AI / ML model from the NRT-RIC framework; requesting the retrained AI / ML model from the NRT-RIC framework by the rApp; Sending the retrained AI / ML model to the rApp via the NRT-RIC framework; 16. The non-transitory computer-readable storage medium of claim 15, comprising:

17. 16. The non-transitory computer-readable storage medium of claim 15, wherein retraining the at least one AI / ML model comprises retraining, by the rApp, one AI / ML model from the plurality of AI / ML models.

18. the O1-related data providing the O1 configuration necessary to perform the RF channel reconfiguration comprises at least one of a configuration, a performance indicator, and a measurement report provided by the O-RU; the measurement report comprises at least one energy efficiency / energy consumption (EE / EC) measurement report; the energy efficiency / energy consumption (EE / EC) measurement report comprises at least one of: Reference Signal Received Quality (RSRQ) measurements per synchronization signal block (SSB) per cell; Reference Signal Received Power (RSRP) measurements per SSB per cell; Signal-to-Interference-plus-Noise Ratio (SINR) measurements per SSB per cell; energy consumption; power consumed by hardware components; transmit power; per-cell and per-carrier load statistics, such as number of active users, average number of Radio Resource Control (RRC) connections, average number of scheduled active users per Transmission Time Interval (TTI), Physical Resource Block (PRB) utilization, downlink / uplink (DL / UL) cell / user throughput, precoding matrix indicator / channel state information (PMI / CSI) reports, per-cell latency statistics, and power consumption metrics information on supported Tx / Rx array selections along with power consumption Key Performance Indicators (KPIs); 16. The non-transitory computer-readable storage medium of claim 15.

19. collecting the O1-related data that provides an O1 configuration necessary to perform the RF channel reconfiguration includes: sending, by the rApp, an O1-related data collection request to the E2 node via an R1 interface through the NRT-RIC framework and via an O1 interface through the SMO function in the SMO framework; receiving, by the E2 node, the O1-related data collection request from the SMO function; collecting, by the E2 node, from the open radio unit (O-RU) via an open fronthaul management plane (FH M-Plane) interface between the E2 node and the O-RU, the O1-related data providing an O1 configuration required to perform the RF channel reconfiguration; sending, by the E2 node, the O1-related data to the rApp via the R1 interface, providing the O1 configuration necessary to perform the SMO function within the SMO framework and the RF channel reconfiguration collected via the O1 interface through the NRT-RIC framework; 16. The non-transitory computer-readable storage medium of claim 15, comprising:

20. 16. The non-transitory computer-readable storage medium of claim 15, wherein the O1 configuration data for preparing and performing the RF channel reconfiguration comprises at least one of an O-RU Tx / Rx array selection, a change in the number of SU / MU MIMO spatial streams or data layers, a change in the number of SSB beams, and a change in the antenna transmit power of the O-RU.

Images