Implementing advanced sleep mode in telecommunications network

Abstract

Systems and methods for implementing an advanced sleep mode in an O-RAN, the method comprising: collecting measurement data for training an AI / ML model; training an AI / ML model based on the collected measurement data, and deploying the AI / ML model in an nRT-RIC; the trained AI / ML model is activated in the nRT-RIC; monitoring, via the E2 node, energy optimization data from AI / ML model reasoning of an open radio unit (O-RU); activating at least one advanced sleep mode (ASM) in the nRT-RIC; collecting data for temporarily deactivating the O-RU component based on the activation of the ASM; evaluating the collected data for temporarily deactivating the O-RU component based on the activated AI / ML model and the ASM; based on the evaluation, requesting to initiate ASM to the O-RU; and initiating a request based on the ASM, and realizing the ASM by the E2 node and the O-RU.

Description

[0001] Cross - Reference to Related Applications

[0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 481,637, filed on January 26, 2023, the entire content of which is incorporated herein by reference. Technical Field

[0003] The present disclosure relates to implementing an advanced sleep mode to reduce the power consumption of radio base stations (BSs) in a telecommunications network. Background Art

[0004] The radio access network (RAN) is an important part of a telecommunications system as it 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 is vendor-specific.

[0005] Open RAN (O-RAN) technology has emerged to enable multiple vendors to supply hardware and / or software to a telecommunications system. To this end, O-RAN decomposes RAN functions into an open central 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 radio resource control (RRC), service data adaptation protocol (SDAP), and / or packet data convergence protocol (PDCP) sublayers of the RAN. The O-DU is a logical node for hosting the radio link control (RLC), media access control (MAC), and physical (PHY) sublayers of the O-RAN. The O-RU is a physical node that converts radio signals from an antenna into digital signals that can be sent to the O-DU via fronthaul (FH). Because of the open protocols and interfaces between these entities, they can be developed by different vendors.

[0006] In the prior art, the power consumption of a base station BS (e.g., an Open Radio Unit O-RU) varies with the change of cell traffic. As the traffic increases, the physical components of the (multiple) O-RUs (e.g., the RF Front End Module (RFFE) (e.g., the (multiple) Power Amplifiers (PAs), the (multiple) Radio Frequency (RF) Transceivers TRx, etc.)) become the main power consumers. However, in a low-traffic scenario, the main power consumption comes from functional components (i.e., processing devices), such as the Digital RF Front End (DFE), the (multiple) lower PHY layer baseband processing functions, and the (multiple) synchronization and fronthaul transmission functions become the main power consumers. In addition, in the prior art, the (multiple) O-DUs and / or the (multiple) O-CUs (i.e., the (multiple) E2 nodes) may have to support multiple technologies (i.e., depending on the specific scenario and network deployment), and these technologies may affect the power consumption and may also depend on the load (e.g., network traffic, the number of users, etc.).

[0007] For this reason, since the (multiple) E2 nodes (e.g., O-DUs, O-CUs, etc.) may not know the internal architecture of the multi-vendor O-RU design (i.e., the capabilities of the functions and physical components of the (multiple) O-RUs), a drawback of the prior art is that even in the absence of transmission, some parts of the O-RU (e.g., the functional part and / or the physical part) will continue to consume energy.

[0008] Therefore, according to the prior art, the advanced (i.e., blanket) energy-saving modes provided occasionally according to performance goals (e.g., via A1 policies, performance triggers based on O-RAN Key Performance Indicators (KPIs) (e.g., data traffic, data throughput), etc.) are limited to the energy-saving models applied by the O-DU, without knowing the energy-saving capabilities of the O-RU (e.g., the internal system architecture of the O-RU, such as the capabilities of the physical components and / or functional components of the O-RU). Therefore, the energy-saving models applied to the O-RU according to the prior art (i.e., the blanket energy-saving modes) may lead to poor application of these energy-saving modes due to the lack of understanding of the component capabilities of the O-RU, resulting in unnecessary power consumption.

[0009] In addition, considering the local or network-wide impact of the energy-saving modes in O-RAN, there is a trade-off between system performance and energy saving. Therefore, according to the prior art, it is a difficult and complex task to implement energy-saving modes while maintaining the high overall network performance of O-RAN. For example, other carriers and / or cells may have to cover (i.e., take over or serve) additional network traffic, and the network traffic varies over time.

[0010] For this reason, the prior art lacks an abstraction level for effectively balancing system performance and energy saving.

[0011] Therefore, although the energy-saving mode in the prior art can maximize the energy saving of an O-RU on a local basis, the overall network performance of O-RAN may be reduced due to the complex task of balancing system performance and energy saving. Summary of the Invention

[0012] According to an embodiment, the present disclosure relates to implementing an Advanced Sleep Mode (ASM) that enables a Near Real-Time Radio Access Network Intelligent Controller (nRT-RIC) to consider multiple data dimensions, such as traffic load, user service type, and energy efficiency measurements, O-DU capabilities, O-RU capabilities, etc., to determine which ASM (i.e., which level or type of ASM) is most suitable for application by an Energy Saving (ES) function to achieve an optimal balance between system performance and energy saving. Finally, each level of the ASM (i.e., the type of ASM) includes one or more intelligent scheduling features associated with the corresponding ASM level / type, and each intelligent scheduling feature among the one or more intelligent scheduling features applied by the O-DU and / or O-CU to the O-RU results in different power consumption levels of the (multiple) O-RU components (i.e., the physical components and / or functional components of the O-RU).

[0013] In particular, one or more intelligent scheduling features may include scheduling of time slots and / or symbols (e.g., through data aggregation (traffic shaping)), where the (intelligent scheduling features (e.g., scheduling) associated with one or more ASM types / levels have the advantage of allowing for temporary deactivation (mute / shutdown) of O-RU components, which optimizes the power consumption of the O-RU.

[0014] Therefore, considering the capability data of the O-RU and / or O-DU, implementing one or more ASM types / levels can enable an abstract level of the energy-saving mode, thereby achieving the best operational energy efficiency of the (multiple) O-RUs while maintaining a high level of network performance of the entire O-RAN.

[0015] According to an embodiment, a system for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN) includes: a near-real-time Radio Access Network (RAN) Intelligent Controller (nRT-RIC) and a Service Management and Orchestration (SMO) framework. The SMO framework includes a Non-Real-Time Radio Access Network (RAN) Intelligent Controller (NRT-RIC). The system is configured to: collect measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model by the SMO framework; train the AI / ML model by the NRT-RIC based on the collected measurement data and deploy the AI / ML model in the nRT-RIC; activate the trained AI / ML model in the nRT-RIC by the SMO framework; monitor energy optimization data of AI / ML model inference from an Open Radio Unit (O-RU) by the NRT-RIC via an E2 node; activate at least one Advanced Sleep Mode (ASM) in the nRT-RIC by the SMO framework; collect data for temporarily deactivating one or more O-RU components from the O-RU by the nRT-RIC via the E2 node based on the activation of at least one ASM; evaluate the collected data for temporarily deactivating one or more O-RU components by the nRT-RIC based on the activated AI / ML model and at least one ASM; request to initiate at least one ASM to the O-RU by the nRT-RIC via the E2 node based on the evaluation; and implement at least one ASM by the O-RU based on the ASM initiation request.

[0016] According to an embodiment, a method for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN) includes: collecting measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model by a Service Management and Orchestration (SMO) framework; training the AI / ML model by a Non-Real-Time Radio Access Network (RAN) Intelligent Controller (NRT-RIC) based on the collected measurement data and deploying the AI / ML model in a Near-Real-Time Radio Access Network Intelligent Controller (nRT-RIC); activating the trained AI / ML model in the nRT-RIC by the SMO framework; monitoring, by the NRT-RIC via an E2 node, energy optimization data of AI / ML model inference from an Open Radio Unit (O-RU); activating at least one Advanced Sleep Mode (ASM) in the nRT-RIC by the SMO framework; collecting, based on the activation of the at least one ASM, by the nRT-RIC via the E2 node, data for temporarily deactivating one or more O-RU components from the O-RU; evaluating, by the nRT-RIC, the collected data for temporarily deactivating one or more O-RU components based on the activated AI / ML model and the at least one ASM; requesting, based on the evaluation, by the nRT-RIC via the E2 node, to initiate at least one ASM to the O-RU; and implementing, by the O-RU, at least one ASM based on the ASM initiation request.

[0017] According to an embodiment, a non-transitory computer-readable recording medium has instructions recorded thereon that are executable by at least one processor, the processor being configured to implement a method for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN). The method includes: collecting measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model by a Service Management and Orchestration (SMO) framework; training the AI / ML model by a Non-Real-Time Radio Access Network (RAN) Intelligent Controller (NRT-RIC) based on the collected measurement data and deploying the AI / ML model in a Near-Real-Time Radio Access Network Intelligent Controller (nRT-RIC); activating the trained AI / ML model in the nRT-RIC by the SMO framework; monitoring, by the NRT-RIC via an E2 node, energy optimization data from an Open Radio Unit (O-RU) for AI / ML model inference; activating at least one Advanced Sleep Mode (ASM) in the nRT-RIC by the SMO framework; collecting, based on the activation of at least one ASM, by the nRT-RIC via the E2 node, data for temporarily deactivating one or more O-RU components from the O-RU; evaluating, by the nRT-RIC, the collected data for temporarily deactivating one or more O-RU components based on the activated AI / ML model and at least one ASM; requesting, based on the evaluation, by the nRT-RIC via the E2 node, to initiate at least one ASM to the O-RU; and implementing, by the O-RU, at least one ASM based on the ASM initiation request.

[0018] Additional aspects will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the presented embodiments of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Certain example embodiments of the present disclosure will be described below with reference to the accompanying drawings, in which like reference numerals represent like elements, and in which:

[0020] Figure 1 illustrates an O-RAN architecture in the prior art;

[0021] Figure 2 illustrates a diagram of an example environment in which the systems and / or methods described herein can be implemented;

[0022] Figure 3 illustrates a diagram of example components of a device according to an embodiment;

[0023] Figure 4 illustrates an SMO / NRT-RIC framework system architecture according to an embodiment, the architecture being configured to optimize partial shutdown of O-RU components based on A1 policies;

[0024] Figure 5 The figure shows a flowchart of a method for implementing an advanced sleep mode according to an embodiment;

[0025] Figure 6 The figure shows a flowchart of a method for collecting data for temporarily deactivating one or more O-RU components based on the activation of at least one ASM according to another embodiment;

[0026] Figure 7A The figure shows a flowchart of a method for evaluating the collected data for temporarily deactivating one or more O-RU components according to an embodiment;

[0027] Figure 7B The figure shows a flowchart of a method for evaluating the collected data for temporarily deactivating one or more O-RU components according to an embodiment;

[0028] Figure 8 The figure shows a flowchart of a method for implementing an advanced sleep mode according to an embodiment;

[0029] Figure 9 Shows various types of advanced sleep modes according to an embodiment;

[0030] Figure 10 The figure shows a method for scheduling at least one symbol to minimize the number of symbols in the time domain according to an embodiment;

[0031] Figure 11 The figure shows a method for scheduling at least one time slot to minimize the number of time slots in the time domain according to an embodiment;

[0032] Figure 12A The figure shows a method for collecting data via the O1 interface in a hierarchical O-RAN architecture according to an embodiment;

[0033] Figure 12B The figure shows a method for collecting data via the O1 interface in a hybrid O-RAN architecture according to an embodiment;

[0034] Figure 13 The figure shows a method for training an AI / ML model and deploying the AI / ML model in an nRT-RIC according to an embodiment;

[0035] Figure 14 The figure shows a method for activating at least one advanced sleep mode (ASM) in an nRT-RIC by an SMO framework; and

[0036] Figure 15 The figure shows a method for collecting data for temporarily deactivating one or more O-RU components based on the activation of at least one ASM according to an embodiment. Detailed Implementation Modes

[0037] The following detailed description of example embodiments refers to the accompanying drawings. The above disclosure provides illustration and description, but is not intended to be exhaustive or to limit the implementation to the precise forms disclosed. Modifications and variations are possible in light of the above disclosure, or may be obtained from the practice of the implementation. Additionally, one or more features or components of one embodiment may be incorporated into or combined with those of another embodiment (or one or more features of another embodiment). Further, in the flowcharts and operation descriptions provided below, it can be understood that one or more operations may be omitted, one or more operations may be added, one or more operations may be performed simultaneously (at least in part), and the order of one or more operations may be switched.

[0038] Obviously, the systems and / or methods described herein can 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 does not limit these implementations. Thus, the operations and behaviors of the systems and / or methods are described herein without reference to specific software code. It should be understood that software and hardware can be designed to implement these systems and / or methods based on the description herein.

[0039] Even if specific combinations of features are recited in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosed implementations. In fact, many of these features can be combined in ways not specifically recited in the claims and / or not disclosed in the specification. Although each dependent claim listed below may directly depend on only one claim, the disclosed implementations may include combinations of each dependent claim with every other claim in the claim set.

[0040] Unless explicitly stated otherwise, any element, act, or instruction used herein should not be construed as critical or essential. Additionally, as used herein, the terms "a" and "an" are intended to include one or more articles and may be used interchangeably with "one or more." If only one article is intended, the term "one" or similar language is used. Further, as used herein, the terms "has," "have," "having," "include," "including," etc. are intended to be open-ended terms. Additionally, unless otherwise explicitly stated, the term "based on" means "at least partially based on." Further, expressions such as "at least one of [A] and [B]" or "at least one of [A] or [B]" should be understood to include only A, only B, or both A and B. Figure One

[0041] ​The radio access network (RAN) is an important part of a telecommunications system as it connects end-user devices (or user equipment) to the rest of the network. The RAN consists of a combination of various network elements (NEs) that connect end-user devices to the core network. Traditionally, the hardware and / or software of a specific RAN are vendor-specific.

[0042] Open RAN (O-RAN) technology has emerged to enable multiple vendors to provide hardware and / or software to a telecommunications system. To this end, O-RAN decomposes RAN functions into a central unit (CU), a distributed unit (DU), and a radio unit (RU). The CU is a logical node for hosting the radio resource control (RRC), service data adaptation protocol (SDAP), and / or packet data convergence protocol (PDCP) sub-layers of the RAN. The DU is a logical node for hosting the radio link control (RLC), media access control (MAC), and physical (PHY) sub-layers of the RAN. The RU is a physical node that converts radio signals from antennas into digital signals that can be sent to the DU via fronthaul. Because there are open protocols and interfaces between these entities, they can be developed by different vendors.

[0043] Figure 1 The figure illustrates an existing O-RAN architecture. Refer to Figure 1 , the RAN functions in the O-RAN architecture are controlled and optimized by the RIC. The RIC is a software-defined component that implements modular applications to facilitate multi-vendor operability required in an O-RAN system. The RIC also enables automation and optimization of RAN operations. The RIC is divided into two types: non-real-time RIC (NRT-RIC) and near-real-time RIC (nRT-RIC).

[0044] The NRT-RIC is the control point of non-real-time control loops and operates on a time scale greater than 1 second within the service management and orchestration (SMO) framework. Its functions are implemented through modular applications called rApps (rApp 1,..., rApp N) and include: providing policy-based guidance and enrichment across the A1 interface, which is the interface enabling communication between the NRT-RIC and the nRT-RIC; performing data analysis; artificial intelligence / machine learning (AI / ML) training and inference for RAN optimization; and / or recommending configuration management actions via the O1 interface, which is the interface connecting the SMO to RAN management elements (e.g., nRT-RIC, O-RAN central unit (O-CU), O-RAN distributed unit (O-DU), etc.).

[0045] The nRT-RIC operates on a time scale between 10 milliseconds and 1 second and is connected via the E2 interface to the O-DU, O-CU (split into an O-CU control plane (O-CU-CP) and an O-CU user plane (O-CU-UP)), and the Open eNodeB (O-eNB). The nRT-RIC uses the E2 interface to control the underlying RAN elements ((multiple) E2 nodes / network functions (NFs)) in a near-real-time control loop. The nRT-RIC monitors, suspends / stops, overrides, and controls ((multiple) E2 nodes (O-CU, O-DU, and O-eNB)) via policies. For example, the nRT-RIC sets policy parameters for the activation functions of ((multiple) E2 nodes). In addition, the nRT-RIC hosts xApps to implement functions such as quality of service (QoS) optimization, mobility optimization, slice optimization, interference mitigation, load balancing, security, etc. These two types of RICs work together to optimize the O-RAN. For example, the NRT-RIC provides, via the A1 interface, the policies, data, and artificial intelligence / machine learning AI / ML models implemented 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 work).

[0046] The SMO framework in which the NRT-RIC resides manages and orchestrates RAN elements. Specifically, the SMO manages and orchestrates the so-called O-Ran cloud (O-cloud). The O-cloud is a collection of physical RAN nodes that host the RIC, O-CU, and O-DU, support software components (e.g., operating systems and runtime environments), and the SMO itself. In other words, the SMO manages the O-cloud internally. The O2 interface is the interface between the SMO and the O-cloud in which it resides. Through the O2 interface, the SMO provides infrastructure management services (IMS) and deployment management services (DMS).

[0047] On the other hand, the O-cloud is a cloud computing platform that includes a set of physical infrastructure nodes that meet the O-RAN requirements to host the relevant O-RAN functions (e.g., nRT-RIC, O-CU-CP, O-CU-UP, O-DU, etc.), support software components (such as operating systems, hypervisors, container runtimes, etc.), and appropriate management and orchestration functions.

[0048] The SMO framework where the NRT-RIC is located manages and orchestrates RAN elements. The SMO performs the management and orchestration of RAN elements through four key interfaces: the A1 interface between the NRT-RIC and the nRT-RIC in the SMO for RAN optimization; the O1 interface between the SMO and the O-RAN network function for FCAPS support; in the case of a hybrid model, the open front-end M-plane interface between the SMO and the O-RU for FCAPS support; and the O2 interface between the SMO and the O-cloud for platform resource and workload management.

[0049] Figure 2 A diagram illustrating an example environment 200 in which the systems and / or methods described herein can be implemented. As Figure 2 shown, the environment 200 can include user equipment 210, a platform 220, and a network 230. The devices of the environment 200 can be interconnected via a wired connection, a wireless connection, or a combination of wired and wireless connections. In an embodiment, any of the functions and operations referenced above Figure 1 can be performed by any combination of the elements Figure 2 shown.

[0050] The user equipment 210 includes one or more devices capable of receiving, generating, storing, processing, and / or providing information associated with the platform 220. For example, the user equipment 210 can 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 a similar device. In some implementations, the user equipment 210 can receive information from the platform 220 and / or send information to the platform 220.

[0051] The platform 220 includes one or more devices capable of receiving, generating, storing, processing, and / or providing information. In some implementations, the platform 220 can include a cloud server or a group of cloud servers. In some implementations, the platform 220 can be designed to be modular such that certain software components can be swapped in or out according to specific needs. Thus, the platform 220 can be easily and / or quickly reconfigured for different uses.

[0052] In some implementations, as shown, the platform 220 can be hosted in a cloud computing environment 222. It is noted that although the implementations described herein describe the platform 220 as being hosted in the cloud computing environment 222, in some implementations, the platform 220 can be non-cloud-based (i.e., can be implemented outside of a cloud computing environment), or can be partially cloud-based.

[0053] The cloud computing environment 222 includes an environment that hosts the platform 220. The cloud computing environment 222 can provide services such as computing, software, data access, storage, etc., without the end user (e.g., user device 210) knowing the physical location and configuration of the system(s) and / or device(s) of the hosting platform 220. As shown, the cloud computing environment 222 can include a set of computing resources 224 (collectively referred to as "computing resources 224" and individually as "computing resource 224").

[0054] The computing resources 224 include one or more personal computers, clusters of computing devices, workstation computers, server devices, or other types of computing and / or communication devices. In some implementations, the computing resources 224 can host the platform 220. Cloud resources can include computing instances executed in the computing resources 224, storage devices provided in the computing resources 224, data transfer devices provided by the computing resources 224, etc. In some implementations, the computing resources 224 can communicate with other computing resources 224 via a wired connection, a wireless connection, or a combination of wired and wireless connections.

[0055] As Figure 2 Further shown, the computing resources 224 include a set 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, one or more hypervisors ("HYP") 224-4, etc.

[0056] The application 224-1 includes one or more software applications that can be provided to or accessed by the user device 210. The application 224-1 can eliminate the need to install and execute software applications on the user device 210. For example, the application 224-1 can include software associated with the platform 220 and / or any other software that can be provided via the cloud computing environment 222. In some implementations, one application 224-1 can send information to / receive information from one or more other applications 224-1 via the virtual machine 224-2.

[0057] The virtual machine 224-2 includes a software implementation of a machine (e.g., a computer), such as a physical machine, that executes programs. The virtual machine 224-2 can be a system virtual machine or a process virtual machine, depending on the degree of use and correspondence of the virtual machine 224-2 with any real machine. A system virtual machine can provide a complete system platform that supports the execution of a complete operating system (“OS”). A process virtual machine can execute a single program and can support a single process. In some implementations, the virtual machine 224-2 can execute on behalf of a user (e.g., the user device 210) and can manage the infrastructure of the cloud computing environment 222, such as data management, synchronization, or long-duration data transfer.

[0058] The virtualized storage 224-3 includes one or more storage systems and / or one or more devices that use virtualization techniques within a storage system or device of the computing resources 224. In some implementations, in the context of a storage system, the types of virtualization can include block virtualization and file virtualization. Block virtualization can refer to the abstraction (or separation) of logical storage from physical storage such that the storage system can be accessed without regard to the physical storage or heterogeneous structure. This separation can allow the administrator of the storage system to have flexibility in how the administrator manages storage for end users. File virtualization can eliminate the dependency between the data accessed at the file level and the location where the file is physically stored. This can enable performance for optimizing storage use, server consolidation, and / or seamless file migration.

[0059] The hypervisor 224-4 can provide hardware virtualization technology that allows multiple operating systems (e.g., “guest operating systems”) to execute simultaneously on a host, such as the computing resources 224. The hypervisor 224-4 can present a virtual operating platform to the guest operating systems and can manage the execution of the guest operating systems. Multiple instances of various operating systems can share the virtualized hardware resources.

[0060] The network 230 includes one or more wired and / or wireless networks. For example, the network 230 can include cellular networks (e.g., fifth-generation (5G) networks, long-term evolution (LTE) networks, third-generation (3G) networks, code division multiple access (CDMA) networks, etc.), public land mobile networks (PLMNs), local area networks (LANs), wide area networks (WANs), metropolitan area networks (MANs), telephone networks (e.g., public switched telephone networks (PSTNs)), private networks, ad hoc networks, intranets, the Internet, fiber-based networks, etc., and / or combinations of these or other types of networks.

[0061] Figure 2 The number and arrangement of the devices and networks shown are provided as an example. In practice, there may be Figure 2more devices and / or networks, fewer devices and / or networks, different devices and / or networks, or differently arranged devices and / or networks than shown. Additionally, Figure 2 two or more of the devices shown may be implemented within a single device, or Figure 2 a single device shown may be implemented as multiple distributed devices. Additionally or alternatively, a set of devices (e.g., one or more devices) of environment 200 may perform one or more functions described as being performed by another set of devices of environment 200.

[0062] Figure 3 A diagram illustrating example components of device 300. Device 300 may correspond to user device 210 and / or platform 220. As Figure 3 shown, device 300 may include bus 310, processor 320, memory 330, storage component 340, input component 350, output component 360, and communication interface 370.

[0063] Bus 310 includes components that permit communication between the components of device 300. Processor 320 may be implemented in hardware, firmware, or a combination of hardware and software. Processor 320 may be a central processing unit (CPU), graphics processing unit (GPU), accelerated processing unit (APU), microprocessor, microcontroller, digital signal processor (DSP), field programmable gate array (FPGA), application specific integrated circuit (ASIC), or other type of processing component. In some implementations, processor 320 includes one or more processors that can be programmed to perform functions. Memory 330 includes random access memory (RAM), read only memory (ROM), and / or another type of dynamic or static storage device that stores information and / or instructions for use by processor 320 (e.g., flash memory, magnetic memory, and / or optical memory).

[0064] 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 disc (CD), a digital versatile disc (DVD), a floppy disk, a cassette tape, a magnetic tape, and / or another type of non-transitory computer-readable medium, as well as corresponding drives. Input component 350 includes components that permit device 300 to receive information such as via user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, and / or a microphone). Additionally or alternatively, input component 350 may include sensors for sensing 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)).

[0065] The communication interface 370 includes transceiver-like components (e.g., a transceiver and / or separate receiver and transmitter) that enable the device 300 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. The communication interface 370 may allow the device 300 to receive information from and / or provide information to another device. For example, the communication 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.

[0066] The device 300 may perform one or more of the processes described herein. The device 300 may perform these processes in response to the processor 320 executing software instructions stored by a non-transitory computer-readable medium such as the memory 330 and / or the storage component 340. A computer-readable medium is defined herein as a non-transitory memory device. A memory device includes a memory space within a single physical storage device or a memory space distributed across multiple physical storage devices.

[0067] The software instructions may be read into the memory 330 and / or the storage component 340 from another computer-readable medium or from another device via the communication interface 370. When executed, the software instructions stored in the memory 330 and / or the storage component 340 may cause the processor 320 to perform one or more of the processes described herein.

[0068] Additionally or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more of the processes described herein. Accordingly, the implementations described herein are not limited to any particular combination of hardware circuitry and software.

[0069] Figure 3 The number and arrangement of the components shown are provided as an example. In practice, the device 300 may include more components, fewer components, different components, or differently arranged components than those shown. Additionally or alternatively, a set of components (e.g., one or more components) of the device 300 may perform one or more functions described as being performed by another set of components of the device 300. Figure 3 In an embodiment,

[0070] any one of the operations or processes of Figure 4 、 Figure 5 、 Figure 6 、Figure 7 and Figure 8 may be implemented by or using Figure 1 、 Figure 2 and Figure 3implemented by any of the elements shown. It should be understood that other embodiments are not limited thereto and can be implemented in various different architectures (e.g., bare-metal architecture, any cloud-based architecture or deployment architecture such as Kubernetes, Docker, OpenStack, etc.).

[0071] Figure 4 Illustrated is an SMO / NRT-RIC framework system architecture configured to implement an advanced sleep mode according to an embodiment.

[0072] Referring Figure 4 , the NRT-RIC framework and the NRT-RIC within the NRT-RIC framework represent a functional subset of the SMO framework. The NRT-RIC can access other SMO framework functions and thereby affect (i.e., control and / or execute) the content carried on the O1 and O2 interfaces (e.g., perform configuration management (CM) and / or performance management (PM)).

[0073] The SMO framework system architecture includes an SMO function, which includes an O1 terminal that enables communication between the SMO framework and (multiple) E2 nodes (i.e., O-CU, O-DU, etc.) via the O1 interface.

[0074] The SMO framework system architecture includes an SMO function, which includes an O2 terminal that enables communication between the SMO framework and (multiple) E2 nodes (i.e., O-CU, O-DU, etc.) via the O2 interface.

[0075] The NRT-RIC includes an NRT-RIC framework. In addition to multiple other functions, the NRT-RIC / framework also includes an R1 service exposure function for processing R1 services provided according to an example embodiment, etc. Generally, the NRT-RIC functions within the NRT-RIC framework support authorization, authentication, registration, discovery, communication support, etc. for rAPPs.

[0076] Generally, R1 services can include a series of services, including but not limited to service registration and discovery services, authentication and authorization services, AI / ML workflow services, and services related to the A1, O1, and O2 interfaces.

[0077] An NRT-RIC application (rApp) is an application that utilizes the functions available in the NRT-RAC framework and / or the SMO framework to provide value-added services related to RAN operation and optimization. The scope of rApp includes but is not limited to radio resource management, data analysis, etc., and information enrichment. Generally, an rApp refers to an application designed to consume and / or produce R1 services.

[0078] To this end, the NRT-RIC framework generates and / or consumes R1 services via the R1 interface according to the example embodiments. The R1 interface terminates at the R1 terminator of the NRT-RIC framework. The R1 terminator is connected to the NRT-RIC framework and the rApp via the R1 interface, and enables the NRT-RIC framework and the rApp to exchange messages / data (i.e., requests and responses including data models) to access the R1 services via the R1 interface.

[0079] Generally, the R1 interface is defined as the interface between the rApp and the NRT-RIC framework, via which R1 services can be produced and consumed.

[0080] In addition, the NRT-RIC framework includes A1-related functions. The A1-related functions of the NRT-RIC framework support, for example, A1 logical terminators, A1 policy coordination and cataloging, A1-EI coordination and cataloging, etc.

[0081] In particular, the NRT-RIC framework and the A1-related functions therein provide A1 policies (i.e., a set of rules used to manage and control changes and / or maintenance of the states of one or more managed objects) based on guidance and enrichment across the A1 interface, which is the interface enabling communication between the NRT-RIC and the nRT-RIC (i.e., according to the prior art, the A1 policy is a declarative policy expressed using formal statements, which enables the NRT-RIC within the SMO to guide the nRT-RIC and thus guide the RAN to better achieve RAN intentions (e.g., predefined performance goals)).

[0082] The data management and exposure service within the NRT-RIC framework delivers data created or collected by data producers to data consumers according to the needs of the data consumers (e.g., delivering function management (FM) / consumption management (CM) / production management (PM) data to the rApp via the O1 interface, or changing CM from the rApp to O-RAN).

[0083] The NRT-RIC framework also includes external terminators. For example, the external terminators support data exchange between the NRT-RIC framework and external AI / ML functions, rich information (EI) sources, or external supervision.

[0084] Within the NRT-RIC framework, the AI / ML workflow service provides access to the AI / ML workflow. For example, the AI / ML workflow service can help train models, monitor AI / ML models deployed in the NRT-RIC, etc. Therefore, the NRT-RIC framework and the AI / ML workflow service therein enable artificial intelligence and machine learning (AI / ML) training and inference for RAN optimization.

[0085] In addition, the NRT-RIC framework includes A2-related functions that support, for example, A2 logical terminals, A2 policy coordination, and cataloging, etc.

[0086] Reference Figure 4 , the NRT-RIC framework (e.g., at least one rApp hosted by the NRT-RIC and / or the NRT-RIC framework) allows for the flexible parameters of O-RU components (e.g., physical and functional components in the O-RU) in a cell or cell cluster to be temporarily deactivated by providing an A1 policy on the A1 interface, which is formulated by the NRT-RIC (e.g., at least one rApp hosted by the NRT-RIC and / or the NRT-RIC architecture assisted by machine learning (ML) techniques) to the nRT-RIC, where the nRT-RIC can implement the deployment of configuration parameters (e.g., physical and functional components in the O-RU) for temporarily deactivating the O-RU components to one or more E2 nodes via E2 interface actions.

[0087] Reference Figure 4 , the SMO and the NRT-RIC framework are configured to collect data for temporarily deactivating one or more O-RU components (e.g., the SMO and the NRT-RIC framework may include collection and control functions). For example, necessary cell configurations, performance metrics, measurement reports (e.g., cell load-related information and traffic information, energy efficiency EE and / or energy consumption EC measurement reports, geographical location information, etc.) from E2 nodes (i.e., from E2 nodes such as O-CU, O-DU, etc.) and O-RUs (via E2 nodes or directly).

[0088] For example, the data collected for temporarily deactivating one or more O-RU components may include relevant information of the corresponding O-RU(s), where the configuration, performance metrics, and measurement reports (e.g., cell load-related information and traffic information, energy efficiency EE and / or energy consumption EC measurement reports, geographical location information, etc.) enable the identification of the individual capabilities of the O-RU(s) (e.g., the internal system architecture, performance, functions, etc. of the O-RU) to optimally control and / or configure the O-RU components.

[0089] The data collected (e.g., measurement data for energy conservation) can be used to train (retrain) and infer an AI / ML model, which assists the EE / ES function through the SMO / non-RT RIC framework assisted by machine learning (ML) techniques to optimize the energy efficiency EE and / or energy consumption EC towards the nRT-RIC.

[0090] As described above, it is assumed in this document that the configurations, performance metrics, and measurement reports collected from the E2 nodes (i.e., O-DU, O-CU, etc.) (i.e., the data used to perform optimization for the temporary deactivation of (multiple) O-RU components) contain relevant information of the corresponding O-RU components (e.g., the O-RU capabilities for implementing the advanced sleep mode of the physical / functional components).

[0091] According to an example embodiment, the above-collected data can be collected from the O-RU via the O1 interface via the E2 node according to the hierarchical O-RAN system architecture, and / or directly from the O-RU via the open FH M-plane according to the hybrid O-RAN system architecture.

[0092] For example, the above-collected data can be collected from the O-RU via the open FH M-plane via the E2 interface.

[0093] Therefore, the SMO and NRT-RIC frameworks are configured to analyze the data collected from the E2 nodes (e.g., E2 nodes such as O-CU, O-DU, etc.) and / or the O-RU to trigger the advanced sleep mode (ASM).

[0094] Generally, the energy efficiency EE is defined as the relationship between the useful output and the energy / power consumption, and the energy consumption EC is defined as the integral of the power consumption over time.

[0095] In addition, the SMO and NRT-RIC frameworks are configured to formulate and / or provide optimization triggers, optimization objectives (e.g., enabling traffic shaping to extend the sleep mode at 50% peak power consumption), and A1 policies (e.g., intent-based policies) to the nRT-RIC (e.g., via the O1 interface and / or the A1 interface).

[0096] In addition, the SMO and NRT-RIC frameworks can be configured to train, retain, update, configure, etc. the EE / ES AI / ML models in the NRT-RIC.

[0097] In an example embodiment, the SMO framework (i.e., the NRT-RIC) can be configured to activate and deploy the EE / ES AI / ML models in the nRT-RIC.

[0098] Still referring to Figure 4 , Figure 1 the E2 node of

[0099] In addition, an E2 node (e.g., the E2 node) is configured to apply ES functions or execute an advanced sleep mode on an O-RU based on a policy (E2 policy command) or a recommendation (E2 control command) from the nRT-RIC, respectively.

[0100] In addition, an E2 node (e.g., the E2 node) is configured to perform traffic shaping (i.e., intelligent scheduling) to converge symbols and / or time slots from the time domain to the frequency domain to extend the deactivation period of one or more O-RU components and / or execute actions such as adjusting the remaining minimum system information (RMSI) broadcast interval and common channels (e.g., physical downlink control channel), aligning the discontinuous reception (DRX) cycles of user entities (UEs) in a cell, and using a multi-carrier based energy saving method, etc.

[0101] As Figure 1 shown, the O-RU is configured to report advanced sleep mode related capability information to the O-DU via the M-plane.

[0102] In addition, in an exemplary embodiment, the O-RU is configured to perform a transition from an active state to a desired sleep mode (i.e., temporarily deactivate O-RU components based on the type of the advanced sleep mode) according to an indication from an E2 node (i.e., the O-DU) via the CUS-plane.

[0103] In addition, the O-RU is configured to report power consumption and sleep state related information to an E2 node (i.e., the O-DU) and / or the SMO framework via an open FH M-plane according to the hybrid O-RAN system architecture.

[0104] Referring Figure 4 , to prepare and execute a method for implementing an advanced sleep mode in an O-RAN, the SMO framework and the E2 node can extract input data, where among other O1 related data, O2 related data, E2 related data, etc. available in the O-RAN, the input data can include load statistics for each cell and each carrier (e.g., the number of active users, the average number of radio resource control (RRC) connections, the average number of scheduled active users per transmission time interval (TTI), physical resource block (PRB) utilization, downlink DL and / or uplink UL cell / user throughput, precoding matrix indicator (PMI) reports, and / or channel state information (CSI) reports, etc.).

[0105] In addition, to prepare for and execute methods for implementing advanced sleep mode in O-RAN, the SMO framework and the E2 node can also extract input data, such as latency statistics for each cell (e.g., in the case of ultra-reliable low-latency communication (URLLC) slices, the latency can be utilized as defined in EE TS 28.554), O-DU capabilities related to advanced sleep mode (e.g., O-DU capabilities due to specific network scenarios (e.g., traffic load) and network deployments related to advanced sleep mode), etc.

[0106] In addition, to prepare for and execute methods for implementing advanced sleep mode in O-RAN, the O-RU can extract input data, such as power consumption metrics, including, for example, average total power consumption and per-carrier power consumption, power consumption metrics for each type of advanced sleep mode, etc. In addition, the O-RU data can extract information about the O-RU's supported advanced sleep modes (i.e., the O-RU's capabilities related to advanced sleep mode (e.g., the capabilities related to advanced sleep mode of the O-RU's physical and functional components). For example, information about the O-RU's supported advanced sleep modes can include the transition time from sleep to active (e.g., including the cell site / O-RU input power required for a specific energy efficiency (EE) KPI).

[0107] The extracted input data of the SMO framework, E2 node, and O-RU as described above can be collected by the NRT-RIC and / or nRT-RIC for processing methods for implementing advanced sleep mode in O-RAN.

[0108] Reference Figure 4 , to prepare for and execute methods for implementing advanced sleep mode in O-RAN, the communication between the NRT-RIC and the nRT-RIC includes output data available in O-RAN, such as other O1-related data, O2-related data, A1-related data, etc., including output data providing O1-related configuration data (e.g., ES optimization trigger, ES optimization target, etc.) and / or one or more A1 policies for executing advanced sleep mode based on network operator (intent-based) policies.

[0109] In addition, for preparing and executing a method for implementing an advanced sleep mode in O-RAN, the communication between the NRT-RIC and the E2 node (i.e., the E2 node) includes outputting data to one or more O-RU components, such as E2 policy commands and / or E2 control commands, which provide, for example, policies and / or guidelines regarding activating traffic shaping (scheduling of time slots and / or symbols) to minimize the active time slot transmission time interval (TTI) and / or symbol TTI, policies and / or guidelines regarding executing an ASM type (e.g., involving a dormant sleep mode with an expected latency higher than 10 ms), and policies and / or guidelines regarding configuring the common channel (i.e., PDCCH) and the remaining minimum system information (RMSI). In addition, from the E2 node to the O-RU.

[0110] To this end, the E2 policy commands and / or E2 control commands include policies and / or guidelines regarding activating the advanced sleep mode to achieve an optimal balance between system performance and energy saving.

[0111] In addition, for preparing and executing a method for implementing an advanced sleep mode in O-RAN, the communication between the E2 node (i.e., the E2 node) and the O-RU includes outputting data, such as advanced sleep mode execution commands on the CUS-plane. For example, the advanced sleep mode execution commands may include appropriate execution commands for allowing the implementation of an advanced sleep mode that takes into account the O-RU capabilities and achieves an optimal balance between system performance and energy saving.

[0112] As a result, as Figure 4 configured in the O-RAN system architecture, the implementation of one or more ASM types / levels that take into account the capability data of the O-RU and / or O-DU is achieved, enabling an abstraction level of the energy saving mode to allow optimizing the operational energy efficiency of the (multiple) O-RUs while maintaining a high level of network performance of the entire O-RAN.

[0113] Figure 5 FIG. illustrates a flowchart of a method for implementing an advanced sleep mode according to an embodiment.

[0114] Referring to Figure 5 , the method for implementing an advanced sleep mode may include according to Figure 1 and Figure 4functions, such as Service Management and Orchestration (SMO) framework, near-real-time Radio Access Network (RAN) Intelligent Controller (nRT-RIC), non-real-time Radio Access Network (RAN) Intelligent Controller (NRT-RIC), NRT-RIC framework. Additionally, the functions can be implemented in a system for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN), which system can include a memory storing instructions and at least one processor configured to implement a near-real-time Radio Access Network (RAN) Intelligent Controller (nRT-RIC) as well as a Service Management and Orchestration (SMO) framework, where the SMO framework includes: a non-real-time Radio Access Network (RAN) Intelligent Controller (NRT-RIC), and where the at least one processor is configured to execute instructions according to Figure 5 the method for implementing the advanced sleep mode in

[0115] In step 501, the SMO framework collects measurement data required to train an artificial intelligence / machine learning (AI / ML) model.

[0116] For example, necessary cell configurations, performance metrics, measurement reports (e.g., cell load-related information and traffic information, energy efficiency EE and / or energy consumption EC measurement reports, geographical location information, etc.) from E2 nodes (i.e., from E2 nodes such as O-CU, O-DU, etc.) and O-RUs (via E2 nodes or directly), etc.

[0117] In step 502, based on the collected measurement data, the NRT-RIC trains (e.g., retrains) the AI / ML model and deploys the AI / ML model in the nRT-RIC.

[0118] For example, as Figure 4 shown, the NRT-RIC retrieves the measurement data required to train an artificial intelligence / machine learning (AI / ML) model from the SMO framework via the NRT-RIC framework.

[0119] In an example embodiment, the input data for training an AI / ML model may include 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: the amount of downlink packet data convergence protocol service data unit DL PDCP SDU data for each interface (the amount of data in the DL delivered from the O-CU-UP to the O-DU, for each public land mobile network PLMN, for each quality of service QoS level, for each slice, for each F1-U interface, Xn-U interface, X2-U interface), the amount of uplink packet data convergence protocol service data unit UP PDCP SDU data for each interface (the amount of data in the UL delivered from the O-CU-UP to the O-DU, for each public land mobile network PLMN, for each quality of service QoS level, for each slice, for each F1-U interface, Xn-U interface, X2-U interface), the reference signal received quality RSRQ measurement for each cell for each synchronization signal block SSB, the reference signal received power RSRP measurement for each cell for each SSB, the signal-to-interference-plus-noise ratio SINR measurement for each cell for each SSB, energy consumption, power consumed by hardware components, transmit power, etc.

[0120] In step 503, the SMO framework activates the trained AI / ML model in the nRT-RIC.

[0121] In step 504, the NRT-RIC monitors, via the E2 node, the energy optimization data from the AI / ML model inference of the O-RU. For example, the NRT-RIC continuously (e.g., periodically or event-based) monitors the performance and energy consumption of the E2 node and the O-RU for inference. The performance and energy consumption (i.e., the optimization data) may include data such as cell load-related data and traffic information, EE / EC measurement reports, geographical location information, etc.

[0122] In step 505, the SMO framework activates at least one advanced sleep mode (ASM) in the nRT-RIC. For example, the SMO may trigger the activation of at least one advanced sleep mode (ASM) in the nRT RIC via the O1 interface. Alternatively, the NRT-RIC may provide a policy via the A1 interface that directs the nRT-RIC to apply the EE / ES function to activate at least one advanced sleep mode (ASM).

[0123] Furthermore, in step 506, based on the activation of at least one ASM, the nRT-RIC collects, via the E2 interface, from the O-RU via the E2 node, the data required to prepare and execute the temporary deactivation of one or more O-RU components.

[0124] For example, the data required to prepare for and perform a temporary deactivation of one or more O-RU components may include E2 node data, such as latency statistics for each cell (e.g., in the case of ultra-reliable low-latency communication (URLLC) slices, the latency can be exploited as defined in EE TS 28.554), O-DU capabilities related to advanced sleep modes (e.g., O-DU capabilities due to specific network scenarios (e.g., traffic load) and network deployments related to advanced sleep modes), etc.

[0125] In addition, the data required to prepare for and perform a temporary deactivation of one or more O-RU components may include O-RU data, such as power consumption metrics, including, for example, average total power consumption and per-carrier power consumption, power consumption metrics for each type of advanced sleep mode, etc. In addition, O-RU data can extract information about the O-RU's supported advanced sleep modes (i.e., the O-RU's capabilities related to advanced sleep modes). For example, information about the O-RU's supported advanced sleep modes may include the transition time from sleep to active (e.g., including the cell site / O-RU input power required for a specific energy efficiency (EE) KPI).

[0126] In step 507, based on the activated AI / ML model and at least one ASM, the nRT-RIC evaluates the collected data required to prepare for and perform a temporary deactivation of one or more O-RU components. For example, based on AI / ML inference in the nRT-RIC, the nRT-RIC considers the optimization strategy provided in step 505 and analyzes the data collected in step 506 to prepare for and perform a temporary deactivation of one or more O-RU components.

[0127] In step 508, based on this evaluation, the nRT-RIC requests, via the E2 node, to initiate at least one ASM to the O-RU. For example, the nRT-RIC generates an E2 control command that is used to request to initiate at least one ASM to the E2 node that conforms to the O-RU's capabilities; and / or generates an E2 policy command that is used to apply an energy saving (ES) function to the E2 node that conforms to the O-RU's capabilities. In this case, the nRT-RIC can send the E2 control command and / or the E2 policy command to the E2 node via the E2 interface.

[0128] For example, an E2 policy command and / or an E2 control command may provide guidance and / or commands for implementing an optimized policy to request an E2 node to initiate at least an advanced sleep mode (ASM) through the following: activating an intelligent scheduling feature (e.g., scheduling of time slots and / or symbols) to converge symbols or time slots, adjusting the RMSI broadcast interval and common channels, aligning the DRX cycles of UEs in a cell, and further extending the depth and frequency of the sleep mode using a multi-carrier-based energy-saving method (i.e., by clearing (rescheduling) transmission symbols and / or time slots in the time domain for transmission blocks in the frequency domain according to various types / levels of advanced sleep mode (resource blocks (RBs) for symbols and / or resource block groups (RBGs) for time slots) to extend the inactive period of the O-RU without affecting other transmissions to the O-RU).

[0129] According to one example embodiment, an E2 policy command and / or an E2 control command may provide guidance and / or commands to one or more O-RU components, such as for activating an intelligent scheduling feature (e.g., scheduling of time slots and / or symbols) to minimize the active time slot TTI and / or symbol TTI, policies and / or guidance on implementing an ASM type (e.g., involving a dormant sleep mode with an expected latency higher than 10 ms), and policies and / or guidance on adjusting the configuration of a common channel (i.e., PDCCH) and remaining minimum system information (RMSI).

[0130] To this end, an E2 policy command and / or an E2 control command includes policies and / or guidance on activating an advanced sleep mode to achieve an optimal balance between system performance and energy savings.

[0131] In step 509, based on an ASM initiation request, the O-RU implements at least one ASM. For example, an E2 node (i.e., the E2 node) may generate an advanced sleep mode execution command, which is used to request implementation through the CUS-plane. For example, the advanced sleep mode execution command may include appropriate execution commands to allow the implementation of an advanced sleep mode that takes into account the capabilities of the O-RU and achieves an optimal balance between system performance and energy savings.

[0132] Therefore, while considering the capability data of the O-RU and / or O-DU and the data for temporarily deactivating one or more O-RU components, the implemented ASM type (i.e., among multiple types / levels of ASM) allows for the best operational energy efficiency of the (multiple) O-RUs while maintaining a high level of network performance for the entire O-RAN.

[0133] Figure 6 A flowchart illustrating a method for collecting data for temporarily deactivating one or more O-RU components based on the activation of at least one ASM according to another embodiment is shown.

[0134] Reference Figure 6, in step 601, the nRT-RIC sends an energy-saving data collection request to the E2 node via the E2 interface.

[0135] In step 602, the E2 node receives the energy-saving data collection request from the nRT-RIC.

[0136] In step 603, the E2 node collects data for temporarily deactivating one or more O-RU components from the O-RU via the open FH M-plane interface.

[0137] In step 604, the E2 node sends the collected data for temporarily deactivating one or more O-RU components to the nRT-RIC via the E2 interface.

[0138] As a result, Figure 6 the method in Figure 4 allows the collection of data required to temporarily deactivate one or more O-RU components extracted from the input data by the SMO framework, as shown in

[0139] Figure 7A FIG. illustrates a flowchart of a method for evaluating the collected data for temporarily deactivating one or more O-RU components according to an embodiment.

[0140] Referring to Figure 7A , in step 701A, the nRT-RIC receives the collected data for temporarily deactivating one or more O-RU components from the E2 node via the E2 interface.

[0141] In step 702A, based on AI / ML model inference, the nRT-RIC generates at least one E2 control command for requesting to initiate at least one ASM to an E2 node that conforms to the capabilities of the O-RU.

[0142] In step 703A, the nRT-RIC sends at least one E2 control command to the E2 node (e.g., via the E2 interface).

[0143] Figure 7B FIG. shows a flowchart of a method for evaluating the collected data for temporarily deactivating one or more O-RU components according to another embodiment.

[0144] Referring to Figure 7B , in step 701B, the nRT-RIC receives the collected data for temporarily deactivating one or more O-RU components from the E2 node via the E2 interface.

[0145] In step 702B, based on AI / ML model inference, the nRT-RIC generates at least one E2 policy command for the energy saving (ES) function, and the at least one E2 policy command is to be applied to an E2 node that complies with the capabilities of the O-RU;

[0146] In step 703B, the nRT-RIC sends at least one E2 policy command to the E2 node (e.g., via the E2 interface).

[0147] Thus, according to Figure 7A and Figure 7B the embodiments shown in

[0148] Figure 8 Based on the evaluation of the data collected for temporarily deactivating one or more O-RU components, the AI / ML model inference at the nRT-RIC provides one or more E2 control commands and / or at least one E2 policy command for the E2 node to allow for the best operational energy efficiency of the (multiple) O-RUs while maintaining a high level of network performance of the entire O-RAN. Figure 8 FIG. illustrates a flowchart of a method for implementing an advanced sleep mode according to an embodiment. Referring to

[0149] In step 801, based on the implementation, the NRT-RIC receives, via the SMO framework, implementation feedback including a performance analysis of the AI / ML model.

[0150] In step 802, the NRT-RIC analyzes the performance of the AI / ML model in the nRT-NIC.

[0151] In step 803, the NRT-RIC determines that at least one predetermined performance target is not achieved based on the performance of the AI / ML model.

[0152] In step 805, the NRT-RIC initiates a fallback mechanism related to at least one predetermined performance target.

[0153] For example, the NRT-RIC initiates a fallback mechanism to the nRT-RIC (e.g., via the O1 interface and / or the A1 interface), and the mechanism may include: optimization trigger, optimization target (e.g., enabling traffic shaping to extend the sleep mode at 50% peak power consumption), and update of the A1 policy (e.g., intent-based policy). Figure 8The method for implementing the advanced sleep mode provides for the determination of a fallback mechanism (e.g., using a more appropriate advanced sleep mode) related to at least one predetermined performance target based on an analysis of the performance of the AI / ML model in the NRT-NIC. The initiation of the fallback mechanism (i.e., closed-loop control) allows for the adjustment of the ASM type / level in order to respond in a closed-loop manner to changing O-RAN conditions, thereby achieving the best operational energy efficiency of the (multiple) O-RUs while maintaining a high level of network performance for the entire O-RAN.

[0154] Figure 9 Illustrates various types of advanced sleep modes (i.e., ASM type / level) according to an embodiment. Referring to Figure 9 , various types of (advanced) sleep modes (ASM) can be implemented based on the control method and the type of deactivation time scale for deactivating O-RU components. These ASMs can cover most O-RU devices (e.g., (i.e., O-RU components, such as physical and functional components of the O-RU, can be deactivated temporarily).

[0155] In addition, although some O-RUs based on multi-vendor O-RAN FH may not necessarily need to support all types of sleep modes, the O-RU specification (the capabilities of the O-RU) may need to allow for various types of advanced sleep modes (i.e., the O-RU capabilities must support the control methods and (multiple) deactivation time scales used by various types of (advanced) sleep modes (ASM) in order to allow for implementation.

[0156] To this end, the nRT-RIC and / or the O-DU can learn in advance the O-RU specification (the capabilities of the O-RU) in order to apply the ASM supported by the O-RU.

[0157] Accordingly, the O-DU can execute (apply) various types of ASM in the O-RU via the CUS-plane to indicate (message passing) the number of time slots during which the O-RU (i.e., O-RU components) can enter the sleep state.

[0158] According to a first embodiment, a first type of ASM can enable a micro sleep mode (i.e., ASM 1) within the duration based on symbol to time slot (i.e., the temporary deactivation of O-RU components within the duration based on symbol to time slot). For example, ASM 1 can be initiated (e.g., directed) from the nRT-RIC to the O-DU. To this end, the nRT-RIC can send an E2 control command and / or an E2 policy command to the O-DU, where the O-DU can instruct the O-RU to implement ASM 1.

[0159] According to ASM 1 (i.e., the micro-sleep mode), if the E2 node (e.g., gNB) does not need to operate the TX / RX information within the next several Orthogonal Frequency Division Multiplexing (OFDM) symbols (i.e., Truncated OFDM (TOFDM) symbols <T ≤ time slot [ms]), the E2 node can transmit the ability to apply ASM 1 (i.e., the micro-sleep mode) to the nRT-RIC, and the nRT-RIC sends E2 control commands and / or E2 policy commands to the E2 node, where the E2 node indicates to the O-RU that, for example, the radio frequency (RF) transceiver can be turned off within the specified period (e.g., when (re)initiating the O-RU and / or O-DU after power-on and / or maintenance). Alternatively, the nRT-RIC provides an E2 policy command to guide the O-DU, and the O-DU indicates the O-RU according to the E2 policy command.

[0160] For this purpose, the sleep duration of ASM 1 (i.e., the micro-sleep mode) will be based on the O-RU capabilities to support the lowest granularity of sleep intervals (i.e., the finest subdivision of the deactivated state within the symbol-to-time slot duration). The lowest granularity of the sleep interval requires the O-RU components to have the highest level of O-RU capabilities to support the micro-sleep mode).

[0161] Therefore, the ability of the O-RU to support the micro-sleep mode enables the O-DU to make more informed decisions (e.g., generate better efficiency decisions) regarding the application of intelligent scheduling features (e.g., traffic shaping, such as data aggregation of symbols and / or time slots from the time domain to the frequency domain) to save energy.

[0162] The advantage of ASM 1 (i.e., the micro-sleep mode) is that, based on the O-RU capabilities and O-DU capabilities that detect and respond to subtle changes in the traffic pattern, the ability of the O-RU to temporarily deactivate the O-RU components within the symbol-to-time slot duration enables the O-DU to take more precise energy-saving measures instead of relying on broad-based energy-saving strategies.

[0163] According to the second embodiment, another type of ASM can enable the light sleep mode (i.e., ASM 2) within a duration based on (multiple) L time slots (one time slot to 10 ms) (i.e., temporarily deactivate the O-RU components within the duration based on L time slots). For example, the light sleep mode (i.e., ASM 2) can be initiated (e.g., directed) from the nRT-RIC to the O-DU. To this end, the nRT-RIC can send an E2 control command and / or an E2 policy command to the O-DU. According to the light sleep mode (i.e., ASM 2), if the E2 node (e.g., gNB) does not need to operate the TX / RX information within the next L time slots (e.g., time slot ≤ T ≤ 10 ms), the E2 node can convey its ability to apply the light sleep mode (i.e., ASM 2) to the nRT-RIC. The nRT-RIC sends an E2 control command and / or an E2 policy command to the E2 node, where the E2 node instructs the O-RU that, for example, the radio frequency (RF) transceiver and additional hardware components (i.e., other physical O-RU components) can be turned off within the specified period. Alternatively, the nRT-RIC provides an E2 policy command to direct the O-DU, and the O-DU instructs the O-RU according to the E2 policy command.

[0164] To this end, the sleep duration of ASM 2 (i.e., the light sleep mode) is based on the O-RU capability level (i.e., the O-RU capability that supports the temporary deactivation of the (physical) components of the O-RU), which supports a sleep duration (deactivation interval) between one time slot and 10 ms.

[0165] Therefore, in the case of ASM 2 (i.e., the light sleep mode), the power consumption of the O-RU components is generally lower than that of the micro sleep mode (i.e., ASM 1).

[0166] In addition, according to the example embodiment, when there is no synchronization signal block (SSB) in both the downlink (DL) and the physical random access channel (PRACH), or there is no other uplink (UL) signal to be transmitted / received, the light sleep mode can be implemented via transmission blanking.

[0167] According to the third embodiment, another type of ASM can enable the deep sleep mode (i.e., ASM 3) within a duration based on (multiple) M time slots (radio frame to 100 ms) (i.e., temporarily deactivate the O-RU components within the duration based on (multiple) M time slots). For example, the deep sleep mode (i.e., ASM 3) can be initiated (e.g., directed) from the nRT-RIC to the O-DU and the O-RU. To this end, the nRT-RIC can send an E2 control command and / or an E2 policy command to the O-DU, and the E2 node can provide an O-RU implementation instruction command to the O-RU.

[0168] According to the deep sleep mode (i.e., ASM 3), if the E2 node (e.g., gNB) does not need to operate the TX / RX information within the next M time slots (e.g., 10 ms ≤ T ≤ 100 ms), the E2 node can transmit its ability to apply the deep sleep (i.e., ASM 3) to the nRT-RIC. The nRT-RIC sends an E2 control command and / or an E2 policy command to the E2 node, where the E2 node instructs the O-RU to implement the deep sleep mode (i.e., ASM 3). Alternatively, the nRT-RIC provides an E2 policy command to direct the O-DU, and the O-DU instructs the O-RU according to the E2 policy command.

[0169] For example, by initiating the deep sleep mode (i.e., ASM 3), additional hardware components (i.e., other physical O-RU components) can be turned off during the above-specified period. However, according to the deep sleep mode (i.e., ASM 3), some hardware components of the O-RU (such as the timing circuitry) must remain standby or active to allow the O-RU to quickly transition to the active state (i.e., immediate rollback). The power consumption of the deep sleep mode (i.e., ASM 3) is lower than that of the light sleep mode (i.e., ASM 2).

[0170] The sleep duration of the deep sleep mode (i.e., ASM 3) can be based on the O-RU's ability to support sleep durations (i.e., deactivation durations) from radio frames to 100 ms. According to the relatively long deactivation duration, the deep sleep mode (i.e., ASM 3) needs to coordinate with other adjacent cells because if the cell is turned off during the deactivation period according to ASM 3, the user experience will be affected. Therefore, the O-DU may need to schedule and send an O-RU implementation instruction command to the O-RU.

[0171] According to the fourth embodiment, another type of ASM can enable the dormant sleep mode (i.e., ASM 4) within a duration based on (multiple) N time slots (e.g., 100 ms to several seconds) (i.e., temporarily deactivate the O-RU components within a duration based on (multiple) N time slots). For example, the type of ASM that enables the dormant sleep (i.e., ASM 4) can be initiated (e.g., directed) from the nRT-RIC to the O-DU and the O-RU. To this end, the nRT-RIC can send an E2 control command and / or an E2 policy command to the O-DU, and the E2 node can provide an O-RU implementation instruction command to the O-RU.

[0172] According to the dormant sleep mode (i.e., ASM 4), if the E2 node (e.g., gNB) does not need to operate TX / RX information in the next N time slots (e.g., 100 ms to several seconds), the E2 node can transmit its ability to apply deep sleep (i.e., ASM 3) to the nRT-RIC. The nRT-RIC sends E2 control commands and / or E2 policy commands to the E2 node, where the E2 node instructs the O-RU to implement the dormant sleep mode (i.e., ASM 4).

[0173] For example, by initiating the dormant sleep mode (i.e., ASM 4), most hardware components (i.e., almost all physical O-RU components) can be turned off during the aforementioned specified period. However, according to the dormant sleep mode (i.e., ASM 4), some hardware components of the O-RU (such as the timing circuitry) must remain standby or active to allow the O-RU to quickly transition to the active state (i.e., roll back immediately). Compared with the deep sleep mode (i.e., ASM 3), the dormant sleep mode (i.e., ASM 4) has lower power consumption, where sleep durations greater than 1000 ms are not excluded.

[0174] The sleep duration of the dormant sleep mode (i.e., ASM 4) can be based on the O-RU's ability to support sleep durations between 100 ms and several seconds (i.e., deactivation durations). According to the relatively long deactivation duration, the dormant sleep mode (i.e., ASM 4) requires coordination with other adjacent cells because if a cell is turned off during the deactivation period according to ASM 4, the user experience will be affected. Therefore, the O-DU may need to schedule and send O-RU implementation instruction commands to the O-RU.

[0175] Reference Figure 9 , the sleep level (power consumption savings) rises from level 1 to level 4 according to ASM 1 to ASM 4.

[0176] Figure 10 Illustrated is a method for scheduling at least one symbol to minimize the number of symbols in the time domain according to an embodiment. The method for scheduling at least one symbol to minimize the number of symbols in the time domain is associated with an advanced sleep mode, e.g., as Figure 9 shown in.

[0177] Reference Figure 10 , symbols can be allocated in resource blocks (RBs) on various frequency bands in the frequency domain. For example, symbols can be allocated within RB0 to RBn in the frequency domain. Additionally, in the time domain, symbols can be allocated over time (i.e., symbol duration D, such as symbol TTI). For example, symbols are allocated within a symbol duration (e.g., D0 to D13), where the symbol duration has a predetermined period (e.g., symbol TTI).

[0178] To minimize the number of symbols in the time domain (e.g., symbols in the symbol sequence from D0 to D13), the symbols can be relocated to resource blocks (e.g., RB0 to RBn in the corresponding frequency band).

[0179] For example, the symbols of the physical downlink control channel (PDCCH) are allocated within RB0 to RB7 in the frequency domain.

[0180] In addition, the symbols of the physical downlink shared channel (PDSCH) are allocated in 3 resource blocks (RBs) on the symbol sequence from D0 to D13. To save energy, the active time of the O-RU component can be reduced by aggregating symbols from the time domain to the frequency domain. To this end, the symbol sequence D0 to D13 of the PDSCH symbols can be relocated to, for example, RB0 to RB6 in the frequency domain. As a result, 6 symbols of the time domain sequences of PDSCH and PDCCH can be cleared (i.e., the scheduled transmissions can be emptied), and the remaining 7 consecutive symbols are used for PDCCH and PDSCH broadcasts. Therefore, the 6 cleared symbols without data in the time domain can be used as energy-saving time slots (i.e., time slots in which one or more O-RU components are deactivated).

[0181] As a result, aggregating at least one symbol from the time domain to the frequency domain extends the deactivation period of one or more O-RU components. The extended deactivation period enables the E2 node (e.g., gNB) to more frequently identify the state in which the E2 node does not need to operate the TX / RX information within the number of relocated orthogonal frequency division multiplexing (OFDM) symbols (i.e., truncated OFDM (TOFDM) symbols <T≤ES time slot [ms]). The advantage is that the E2 node can transmit the ability to apply, for example, ASM 1, and more frequently initiate the Figure 9 temporary deactivation of the O-RU component as shown in, in order to save energy while maintaining a high level of network performance of the entire O-RAN.

[0182] Figure 11 Illustrated is a method for scheduling at least one time slot to minimize the number of time slots in the time domain according to an embodiment.

[0183] Refer to Figure 11 , the time slots can be allocated in resource block groups (RBGs) within respective frequency bands in the frequency domain. For example, the time slots can be allocated within RBG0 to RBGn in the frequency domain. In addition, in the time domain, the time slots can be allocated over time (i.e., time slot periods, such as time slot TTI). For example, the time slots are allocated within the time slot duration (e.g., time slot 0 to time slot 10), where the time slot duration has a predetermined period (e.g., time slot TTI).

[0184] To minimize the number of time slots in the time domain (e.g., time slots in the time slot sequence from time slot 0 to time slot 10), the time slots can be repositioned to resource block groups (e.g., RBG0 to RBGn in the corresponding frequency band).

[0185] According to the example, in RBG1 to RBG2 of the time slot of the synchronization signal block - master information block (SSB - MIB) in time slot 0, the time slot is scheduled to be transmitted. In RBG3 to RBG5 of time slot 1, the system information block type 1 (SIB1) time slot is scheduled to be transmitted. In time slots 2 and 3, the physical downlink shared channel (PDSCH) time slots are scheduled to be transmitted in RBG1 and RBG2.

[0186] Not limited to this example, for example, the concept of aggregating time slots from the time domain to the frequency domain can be illustrated by the time slots of the physical downlink shared channel (PDSCH), which are scheduled to be transmitted in time slots 2 and 3 (i.e., otherwise time slots 2 and 3 are empty). In this case, the time slots can be aggregated (i.e., rescheduled) to be transmitted in RBG1 to RBG2 of time slots 4 and 5, where there is no transmission load in RBG1 to RBG2 of time slots 4 and 5 (i.e., RBG1 and RBG2 in time slot 4 and time slot 5 are empty). Therefore, time slots 2 and 3 can be cleared from the transmission load in both the time domain and the frequency domain and used to activate ASM (i.e., temporary deactivation of one or more O - RU components).

[0187] In addition, other S1 block time slots can be scheduled to be transmitted in RBG3 to RBG4 of time slots 4 and 5. These time periods are not affected by the above rescheduling.

[0188] In a second example, for example, the concept of aggregating time slots from the time domain to the frequency domain can be illustrated by the time slots of the physical downlink shared channel (PDSCH), which are scheduled to be transmitted in RBG5 through the sequence of time slots 7 to 10. Except for the PDSCH broadcast time slots, there is no transmission load in time slots 7 and 8. To clear time slots 7 and 8, the PDSCH time slots can be rescheduled (i.e., aggregated) to RBG2 and RBG3 of time slots 9 and 10 respectively. Therefore, time slots 7 and 8 can be cleared from the transmission load in both the time domain and the frequency domain and used to activate ASM (i.e., temporary deactivation of one or more O - RU components).

[0189] Reference Figure 10 and Figure 11 , symbol scheduling and time slot scheduling can be supplemented by various traffic shaping techniques (i.e., intelligent scheduling features). These intelligent scheduling features are applied to make such as Figure 10 and Figure 11The symbol scheduling and / or time slot scheduling shown is more flexible (i.e., adjusting the duration of the transmission (symbol or time slot duration) to clear (empty) the maximum number of symbols or time slots in the time domain without affecting other transmissions scheduled in parallel RBs or RBGs).

[0190] In the first traffic shaping example (i.e., according to the first intelligent scheduling feature), the base station (e.g., O-RU) can dynamically adjust the number of PFs (paging frames) sent within a paging cycle (e.g., the paging cycle is called the time interval T in the standard PF). For example, when the O-RAN operates under light or no load (i.e., low utilization of the O-RAN), the number of PFs within the paging cycle is reduced. Alternatively, when the network load is normal (i.e., normal utilization of the O-RAN), the number of PFs within the paging cycle is increased (rolled back).

[0191] Therefore, the dynamic adjustment of the paging frame has the following advantages. That is, by reducing the number of PFs within the paging cycle, the symbols and time slots in the time domain are reduced, making it easier to reschedule (aggregate) the symbols and time slots from the time domain to the frequency domain to clear (empty) the maximum number of symbols or time slots in the time domain without affecting other transmissions scheduled in parallel RBs or RBGs.

[0192] In the second traffic shaping example (i.e., according to the second intelligent scheduling feature), the base station (e.g., O-RU) can dynamically adjust the SSB period. For this purpose, the O-DU and / or O-RU dynamically adjust the period of the SSB from 5 ms to 120 ms based on traffic load and performance-related KPI requirements (such as latency, user throughput, etc.).

[0193] Therefore, the dynamic adjustment of the SSB period can provide the optimal duration to adapt to the corresponding RB and / or RBG, so as to aggregate (reschedule) the SSB transmission from the corresponding symbols and / or time slots in the time domain to the RB and / or RBG of other symbols and / or time slots in the time domain, in order to clear (empty) the maximum number of symbols or time slots in the time domain without affecting other transmissions scheduled in parallel RBs or RBGs.

[0194] In the third traffic shaping example (i.e., according to the third intelligent scheduling feature), the base station (e.g., O-RU) can dynamically adjust the remaining minimum system information (RMSI). For this purpose, for example, the O-RU can dynamically adjust the period of the RMSI and / or other system information (SI) based on traffic load and performance-related KPI requirements (such as latency and user throughput).

[0195] Therefore, the dynamic adjustment of the period of RMSI and / or other system information (SI) can provide the optimal period for transmitting RMSI and / or other system information based on the O-RAN utilization rate, so as to create space for the symbols and time slots to be rescheduled to the corresponding RBs and / or RBGs, thereby aggregating (rescheduling) the corresponding symbols and / or time slots in the time domain to the RBs and / or RBGs of other symbols and / or time slots in the time domain, so as to clear (empty) the maximum number of symbols or time slots in the time domain without affecting other transmissions scheduled in parallel RBs or RBGs.

[0196] In the fourth traffic shaping example (i.e., according to the fourth intelligent scheduling feature), the base station (e.g., O-RU) can dynamically adjust the common channel period. For this purpose, for example, the O-RU can dynamically adjust the period of the physical random access channel (PRACH) and / or other common channels (such as the physical uplink control channel (PUCCH), such as channel state information (CSI) and other reporting information) based on the traffic load and performance-related KPI requirements (such as latency and user throughput).

[0197] Therefore, the dynamic adjustment of the period of RMSI and / or other system information (SI) can provide the optimal period for transmitting RMSI and / or other system information based on the O-RAN utilization rate, so as to create space for the symbols and time slots to be rescheduled to the corresponding RBs and / or RBGs, thereby aggregating (rescheduling) the corresponding symbols and / or time slots in the time domain to the RBs and / or RBGs of other symbols and / or time slots in the time domain, so as to clear (empty) the maximum number of symbols or time slots in the time domain without affecting other transmissions scheduled in parallel RBs or RBGs.

[0198] In the fifth traffic shaping example (i.e., according to the fifth intelligent scheduling feature), the base station (e.g., O-RU) can dynamically adjust the uplink scheduling request (SR). For this purpose, for example, the O-RU can dynamically adjust the uplink SR period based on the ES policy and user performance requirements.

[0199] As a result, the dynamic adjustment of the uplink SR period can optimize the period for transmitting the uplink SR, so as to create space for the symbols and / or time slots to be rescheduled to the corresponding RBs and / or RBGs, thereby aggregating (rescheduling) the corresponding symbols and / or time slots in the time domain to the RBs and / or RBGs of other symbols and / or time slots in the time domain, so as to clear (empty) the maximum number of symbols or time slots in the time domain without affecting other transmissions scheduled in parallel RBs or RBGs.

[0200] In the sixth traffic shaping example (i.e., according to the sixth intelligent scheduling feature), the base station (e.g., O-RU) can dynamically synchronize the discontinuous reception (DRX) cycle of user entities (UEs) in the cell. To this end, the O-DU scheduling mechanism synchronizes the discontinuous reception (DRX) cycle of user entities (UEs) to minimize the O-RU wake-up time (i.e., allow the maximum level of empty symbols / slots to enable deep sleep modes such as ASM 3). Thus, the synchronization of the discontinuous reception (DRX) cycle of user entities (UEs) enables the minimum active time of the O-RU (i.e., the O-RU component), and achieves the best energy efficiency due to the extended deactivation of the O-RU component.

[0201] In the seventh traffic shaping example (i.e., according to the seventh intelligent scheduling feature), the base station (e.g., O-RU) can transfer the traffic of one or more carriers of the O-RU to one or more other carriers according to a multi-carrier scenario. To this end, the O-DU scheduling mechanism can apply the multi-carrier scenario to the corresponding one or more other carriers to extend the deactivation period of the O-RU component scheduled by the O-RU. Thus, the O-DU scheduling mechanism allows the maximum sleep mode duration and the transition to a deeper sleep mode (e.g., from the deep sleep mode (ASM 3) to the dormant sleep mode (ASM 4)).

[0202] Thus, the intelligent scheduling features (e.g., the first to seventh traffic shaping examples) allow the achievement of the deepest possible (optimal) ASM level, resulting in the longest deactivation of one or more O-RU components, and the achievement of this optimal ASM at the lowest granularity level of the sleep interval (i.e., the finest subdivision of the deactivated state within the symbol-to-slot-based duration). This has the advantage of optimizing the abstraction level of the energy-saving mode to allow the best operational energy efficiency of the (multiple) O-RUs while maintaining a high level of network performance of the entire O-RAN.

[0203] Reference Figures 12A to 1 6, The method for implementing the advanced sleep mode (ASM) in the O-RAN enables the ASM energy-saving function in the O-RAN. To this end, the nRT-RIC applies configuration changes to the O-DU and / or O-RU components based on the ASM energy-saving function, and generates control actions and policy settings (e.g., E2 control commands and / or E2 policy commands) using an AI / ML-based solution. For example, the nRT-RIC provides an AI / ML-based E2 policy command to the E2 node (i.e., the O-DU), where the O-DU converts the policy into an O-RU implementation command to instruct the O-RU to implement (i.e., apply and implement) the ASM configuration provided by the nRT-RIC.

[0204] In addition, nRT-RIC controls the application of ASM to the O-DU and / or O-RU. The E2 node and the O-RU configure the corresponding components (e.g., physical and functional O-RU components), and implement execution control actions (e.g., E2 control commands, O-RU implementation commands) and implement policies (e.g., E2 policy commands).

[0205] The SMO and NRT-RIC frameworks formulate policies for triggering and guiding ES optimization in the nRT-RIC.

[0206] Reference Figures 12A to 1 6. After the O-RAN becomes operable (i.e., after an A1 interface connection between the NRT-RIC and the nRT-RIC, an O1 interface connection between the SMO, NRT-RIC and the E2 node, an E2 interface connection between the nRT-RIC and the E2 node, and an open FH M-plane interface connection between the high-layer network functions (SMO, NRT-RIC) and the low-layer network functions (O-DU and / or O-RU) is established), the method for implementing the Advanced Sleep Mode (ASM) starts.

[0207] For example, an open FH M-plane interface connection can be established between the (multiple) E2 nodes and the (multiple) O-RUs (i.e., an open FH M-plane connection according to the hierarchical O-RAN architecture), or an open FH M-plane interface connection can be established between the (multiple) O-RUs and the SMO (i.e., an open FH M-plane connection according to the hybrid O-RAN architecture).

[0208] In addition, according to the state of the operating O-RAN, the nRT-RIC knows the (multiple) overlapping carriers / cells and the coverage of the carriers / cells (e.g., which carrier / cell is the overlay and which is the capacity layer). In addition, according to the state of the operating O-RAN, the nRT-RIC obtains the (performance) targets (e.g., performance policies / targets) provided by the NRT-RIC framework and / or the SMO framework.

[0209] To this end, the network operator can set performance targets for the (multiple) ES functions in the NRT-RIC (i.e., predetermined performance parameters for EE / ES within the O-RAN, e.g., one or more predetermined performance targets for EE / EC in the O-RAN). The targets in the NRT-RIC can be formulated in the corresponding A1 policies.

[0210] Therefore, when the network operator enables the collection and control functions (i.e., optimizing the rApp) and the initial AI / ML model within the SMO framework, the method for implementing ASM can start.

[0211] In addition, based on the performance objectives, the nRT-RIC obtains the ability data of the O-DU and / or O-RU components to support the ASM implementation to achieve the above performance objectives.

[0212] Figure 12A Illustrated is a method for collecting data via the O1 interface in a hierarchical O-RAN architecture. Refer to Figure 12A , Operations 1 to 5 illustrate the data collection for the method of implementing ASM in a hierarchical O-RAN architecture. In Operation 1, the collection and control functions (e.g., rApp) within the SMO framework request to collect measurement data for training an AI / ML model (e.g., NRT-RIC) via the O1 interface.

[0213] In Operation 2, after receiving the request from the SMO framework and / or NRT-RIC framework, the E2 node (i.e., the E2 node, such as O-CU, O-DU, etc.) requests measurement data from the O-RU via the open FH M-plane.

[0214] In Operation 3, the O-RU sends the measurement data to the E2 node via the open FH M-plane interface. In one embodiment, the measurement data may include the status and / or ability data of the O-RU for formulating the objectives of the (multiple) ES functions including the ASM function.

[0215] In Operation 4, the E2 node (i.e., O-CU, O-DU, etc.) sends the measurement data to the SMO framework via the O1 interface, such as the above configuration data, configured measurement data, etc.

[0216] In Operation 5, the NRT-RIC retrieves the measurement data for training the AI / ML model in the NRT-RIC.

[0217] Refer to Figure 12A , The SMO initiates a measurement data collection request to the E2 node and the O-RU for AI / ML model training to achieve energy-saving optimization. The advantage is that, for example, specific measurement data can be extracted from the O-RU during the initialization and reconfiguration of the O-RU (e.g., after updates, maintenance, etc.).

[0218] Figure 12B Illustrated is a data collection method according to another embodiment. Refer to Figure 12B , Operations 1 to 3 illustrate alternative data collection for the method of implementing ASM in a hybrid O-RAN architecture. In Operation 1, the SMO requests to directly collect measurement data for AI / ML model training from the O-RU via the open FH M-plane.

[0219] In operation 2, after receiving a data collection request from the SMO framework, the O-RU sends measurement data to the SMO framework via the open FH M-plane. In one embodiment, the optimization data may include status and / or capability data of the O-DU and / or O-RU for formulating performance objectives including ASM functions. For example, the SMO framework may receive measurement data from the O-RU periodically or based on events.

[0220] In operation 3, the NRT-RIC retrieves measurement data for training the AI / ML model in the NRT-RIC.

[0221] Referring to FIG. 12, according to an example embodiment, the E2 node (i.e., the O-DU) and the O-RU periodically or based on events send configuration measurement data to the SMO for NRT-RIC processing. The periodic communication of the configuration measurement data based on NRT-RIC processing has the advantage that the NRT-RIC can periodically adjust performance objectives (e.g., A1 policies) or train the AI / ML model in the NRT-RIC based on the measurement data.

[0222] Figure 13 Illustrates the AI / ML model training process at the NRT-RIC according to an embodiment. Referring to Figure 13 In operation 1, the NRT-RIC trains the AI / ML model.

[0223] In operation 2, the NRT-RIC deploys the trained AI / ML model to the nRT-RIC, and the SMO framework activates the nRT-RIC via the O1 and A1 interfaces.

[0224] In operation 3, the NRT-RIC continuously monitors the performance of the trained AI / ML model (i.e., the NRT-RIC analyzes the performance of the trained AI / ML model). For example, the NRT-RIC continuously monitors the performance and energy consumption of the E2 node and the O-RU, such as cell load and traffic-related information, EE / EC measurement reports, geographical location information, etc., for AI / ML model inference.

[0225] Figure 14 Illustrates a method for activating ASM according to an embodiment. Referring to Figure 13 In operation 1, the SMO may trigger the activation of the advanced sleep mode in the NRT-RIC via the O1 interface as a performance objective / goal.

[0226] Alternatively, in operation 2, the NRT-RIC may provide a policy via the A1 interface for guiding the nRT-RIC to apply the EE / ES function with the advanced sleep mode.

[0227] Figure 15Illustrated is a method for activating ASM according to an embodiment.

[0228] Referring Figure 15 , in Operations 1 to 7, after the nRT-RIC receives a performance target via the O1 interface or an A1 policy via the A1 interface, the nRT-RIC is based on AI / ML inference in the nRT-RIC, which takes into account an optimization policy (performance trigger) via the O1 interface or an A1 policy via the A1 interface. Additionally, based on an evaluation of measurement data and data for temporarily deactivating one or more O-RU components (such as O-DU and / or O-RU capability data), the nRT-RIC may request the E2 node to prepare and execute an AMS (i.e., generate an E2 control command and / or an E2 policy command).

[0229] For example, in Operation 1, based on the policy guidance of the NRT-RIC, the nRT-RIC requests measurement data from the E2 node via the E2 interface.

[0230] In Operation 2, the E2 node requests the O-RU to provide measurement data (e.g., including data for temporarily deactivating one or more O-RU components).

[0231] In Operation 3, the O-RU sends measurement data (e.g., including data for temporarily deactivating one or more O-RU components) to the E2 node. The E2 node sends measurement data (e.g., including data for temporarily deactivating one or more O-RU components, and the capability data of the O-RU and / or O-DU) to the nRT-RIC.

[0232] In Operation 5, the nRT-RIC evaluates the data collected from the E2 node in Operation 4 (i.e., by analyzing traffic and implementing techniques such as traffic shaping for data aggregation in symbols or time slots, adjusting the RMSI broadcast interval and common channels, aligning the DRX cycles of UEs in the cell, etc.) based on AI / ML inference in the nRT-RIC (taking into account the optimization policy).

[0233] In Operation 6, the nRT-RIC requests the E2 node to initiate the Advanced Sleep Mode (ASM). To this end, the nRT-RIC may also send control actions and / or policies (E2 control commands and / or E2 policy commands) to direct user traffic to different carriers, thereby further expanding the depth and frequency of the ASM.

[0234] In Operation 7, based on the ASM initiation request, the E2 node (i.e., the E2-node) sends an O-RU implementation command to the O-RU. After receiving the O-RU implementation command, the O-RU implements at least one ASM (i.e., the ASM type).

[0235] In Operation 8, as Figure 13As described in operation 2, the NRT-RIC monitors and analyzes the performance of the AI / ML model (e.g., the NRT-RIC can continuously monitor and analyze the performance of the AI / ML model). For example, the NRT-RIC monitors the performance and energy consumption of the (multiple) E2 nodes, the energy consumption of the (multiple) O-RUs, etc.

[0236] In an example embodiment, the input data used in AI / ML model training may include the following measurement data for monitoring the energy consumption and energy efficiency EC / EE of one or more E nodes and one or more O-RUs: the amount of downlink packet data convergence protocol service data unit DL PDCP SDU data for each interface (the amount of data in the DL delivered from the O-CU-UP to the O-DU, for each public land mobile network PLMN, each quality of service QoS level, each slice, each F1-U interface, Xn-U interface, X2-U interface), the amount of uplink packet data convergence protocol service data unit UP PDCP SDU data for each interface (the amount of data in the UL delivered from the O-CU-UP to the O-DU, for each public land mobile network PLMN, each quality of service QoS level, each slice, each F1-U interface, Xn-U interface, X2-U interface), the reference signal received quality RSRQ measurement for each cell each synchronization signal block SSB, the reference signal received power RSRP measurement for each cell each SSB, the signal-to-interference-plus-noise ratio SINR measurement for each cell each SSB, energy consumption, power consumed by the hardware components, transmission power, etc.

[0237] In operation 9, based on the monitoring, the NRT-RIC can determine that a predetermined performance target has not been achieved. In this case, the rApp initiates at least one fallback mechanism related to the predetermined performance target.

[0238] For example, if the performance of the AI / ML model is poor (the predetermined performance target is not achieved), the NRT-RIC modifies the A1 policy. To this end, the NRT-RIC can send the modified A1 policy to the nRT-RIC. For example, the NRT-RIC can update or delete the A1 policy of the ASM energy function and send the modified A1 policy to the nRT-RIC.

[0239] Alternatively, the NRT-RIC can initiate an AI / ML model update and / or an AI / ML model retraining based on the predetermined performance target received by the SMO framework.

[0240] When the (multiple) E2 nodes become inoperable or when the operator disables the SMO framework, the method for implementing the advanced sleep mode can end. However, as long as the SMO framework is enabled, the NRT-RIC continues to monitor the ES functions at the E2 nodes and O-RUs, where the E2 nodes and O-RUs operate with updated parameters / models (i.e., implement the latest commands of the nRT-RIC, including the (multiple) latest E2 control commands and / or the (multiple) latest E1 policy commands, to prepare for and execute the ASM).

[0241] Therefore, by implementing the latest commands from the nRT-RIC, including the (multiple) latest E2 control commands and / or the (multiple) latest E1 policy commands, to prepare for and execute the ASM, while considering the capability data of the O-RU and / or O-DU, the applied ASM type / level allows for the best energy efficiency of the operation of the (multiple) O-RUs, while maintaining a high level of network performance for the entire O-RAN.

[0242] Use cases according to one or more example embodiments will be described below.

[0243]

[0244]

[0245] 7 Advanced Sleep Mode

[0246] Editor's note: This chapter includes a study of the potential impacts and enhancements to O-RAN interfaces, counters, and KPIs in the advanced sleep mode.

[0247] 7.1 Problem Statement, Solution, and Value Proposition

[0248] The power consumption of a radio base station (BS) varies with the cell traffic. As the traffic increases, the power amplifier (PA) becomes the main energy consumer. However, in low-traffic scenarios, the main energy consumption comes from the processing equipment. Even when there is no transmission, some parts of the base station continue to consume energy, which provides an opportunity to reduce unnecessary energy consumption by deactivating unused components.

[0249] The advanced sleep mode (ASM) allows the BS to enter a low-power state when not in use, directly saving energy by intelligently deactivating O-RU sub-components. The decision to implement the ASM is a complex task that requires balancing system performance and energy savings. The near RTRIC is responsible for configuring cell parameters, such as the SSB period, and must consider multiple factors, such as traffic load, user service type, and energy efficiency measurements, in order to make an informed decision on whether to implement the ASM. The impact of the ASM on the O-DU and O-CU energy consumption is flexible and depends on the specific scenario and network deployment. The goal is to achieve energy savings while maintaining a high level of network performance.

[0250] 7.1.1 Background

[0251] This solution involves implementing short and long DRX (Discontinuous Reception) sleep cycles and state transitions in the gNB (gNodeB) in the same way as currently implemented in the UE (User Equipment). The sleep state transition is initiated by the O-DU for the O-RU based on policies or controls provided by the non-RT or near-RT RIC.

[0252] Deeper sleep modes can provide higher energy savings as more devices can be turned off during longer transition times. However, it is important to understand that deeper sleep modes also have a higher transition time from active to sleep and vice versa, so a balance needs to be achieved between energy savings and network user performance.

[0253] 7.1.2 Types of Advanced Sleep Modes

[0254] Defining 4 sleep modes based on the control method and time scale will be sufficient to cover most devices.

[0255] The O-RU based on the O-RAN fronthaul does not necessarily need to support all sleep modes, but it is of no value that the specification needs to consider all possible sleep modes.

[0256] The O-DU can execute the sleep mode in the O-RU through the CUS-plane to indicate the number of time slots in which the O-RU can enter the sleep state.

[0257]

[0258]

[0259]

[0260] 7.1.3 Energy - Saving Intelligent Scheduling Features Associated with Advanced Sleep Modes.

[0261] 7.1.3.1 Data aggregation in symbols

[0262] The base station can use a technique called "frequency domain scheduling" to optimize the transmission of PDSCH data. This technique allows the base station to group the PDSCH data to be transmitted into fewer time domain resources but spread it over more frequency domain resources. This increases the number of symbols without data transmission, thus achieving more efficient utilization of available resources and higher data rates.

[0263] Figure 7.1.3-1: Data aggregation in symbols.

[0264] This feature will support the extension of SM1 (symbol to time slot).

[0265] Data aggregation in slot 7.1.3.2

[0266] By concentrating the scheduling of PDSCH data in the time domain, the base station can increase the number of symbols without data transmission, but it will also increase the scheduling delay to a certain extent.

[0267] One method is to pack data from multiple users into the smallest time slots while allowing an increase in user data delay to improve efficiency.

[0268] Sending PDSCH data (such as Master Information Block (MIB), System Information Block 1 (SIB1), Other System Information (OSI), or paging) in a specific time slot can also be a way to save transmission opportunities.

[0269] Figure 7.1.3-2: Data aggregation in slot

[0270] This feature will support extending SM1 (symbol to slot).

[0271] 7.1.3.3 Dynamic adjustment of SSB period

[0272] Dynamically adjusting the period of SSB from 5 ms to 120 ms based on service load and performance KPI requirements (such as latency and user throughput) can enable deeper sleep modes and longer sleep durations, thus saving more energy.

[0273] It is worth noting that multiple long SS block periods enabling deep modes may have a negative impact on the user experience. Based on the SS blocks of NR cells, devices performing cell reselection and handover may encounter delays in RRM measurements. In addition, they will detect cells with SS block periods higher than 20 ms with a very low probability because the default period assumed by the device is 20 ms. In the LTE system, this is not a problem because PSS / SSS is always sent periodically every 5 ms.

[0274] However, since NR supports sparse synchronization raster, the delay can be avoided. Since many wide-bandwidth frequency bands can be deployed in NR, the device needs to spend an unreasonable amount of time in the cell search process along all possible carrier positions, which is much worse than LTE when there are multiple beams to be captured and paired on both the network and UE sides. The sparse synchronization raster specifically defines the positions where the device must search for SS blocks in the frequency domain. These positions are not always the same as the center frequency in LTE. However, once the device detects an SS block, it will receive all the system information it needs to establish a connection to the cell from the PBCH and SIB1, including information about the subcarrier spacing used for transmission.

[0275] In addition, if the correct SMTC is indicated in the serving cell system information (SI), 5G NR SA cells with an SS block period longer than the default 20 ms can be discovered for cell reselection in the idle / inactive mode. Two SMTCs in the idle / inactive mode are required. In this case, the two SMTCs will coexist in the network: one SMTC for SA cells with an SS block period of 20 ms, which can be detected during initial cell search, and the other SMTC for sleeping cells with an SS block period higher than 20 ms, which can be detected during cell reselection.

[0276] This feature will support extended deep sleep mode and dormant sleep mode

[0277] 7.1.3.4 Dynamic adjustment of RMSI

[0278] Dynamically adjust the periods of RMSI and other SI based on traffic load and performance KPI requirements (such as latency and user throughput).

[0279] This feature will support extended deep sleep mode and dormant sleep mode

[0280] 7.1.3.5 Dynamic adjustment of paging frames

[0281] The base station adjusts the frequency of sending paging frames (PF) based on network traffic. When the traffic is low, the base station sends fewer PFs per paging cycle (PC) to increase the number of symbols without data transmission. When the traffic resumes to the normal level, the base station resumes sending PFs at the original frequency.

[0282] This feature will support extended all ASMs.

[0283] 7.1.3.6 Dynamic adjustment of common channel periods

[0284] Dynamically adjust the periods of PRACH and other common channels (such as PUCCH (CSI and other reports)) based on traffic load, signaling load, and performance KPI requirements (such as latency, jitter, user throughput, packet error rate, and access delay, etc.).

[0285] This feature will support extended all ASMs.

[0286] 7.1.3.7 Dynamic adjustment of uplink scheduling requests

[0287] Dynamically adjust the uplink scheduling request (SR) period based on the ES policy and user performance requirements.

[0288] The purpose is to enable a deeper sleep mode by increasing the SR period of the UE.

[0289] This feature will support extended all ASMs.

[0290] 7.1.3.8 Synchronize the DRX cycle of the UE

[0291] Synchronize the DRX cycle of the UE to minimize the network wake-up time, which can be achieved through the O-DU scheduling mechanism.

[0292] This feature will support extending all ASMs.

[0293] 7.1.3.9 Intelligent scheduling in a multi-carrier scenario

[0294] In a multi-carrier scenario, transfer the user's traffic to other carriers to achieve the maximum sleep duration in the minimum number of cells, which can also improve the network efficiency.

[0295] This feature will support extending all ASMs.

[0296] 7.2 Architecture / Deployment options

[0297] 7.1.4 Solution 1: ASM with a near-RT RIC deployment

[0298] 7.1.4.1 Description and UML diagram

[0299]

[0300]

[0301]

[0302] @startuml

[0303] skin rose

[0304] skinparam defaultFontSize 15

[0305] autonumber

[0306] Box "Service Management &\n Orchestration Framework" #gold

[0307] Participant “Collection & Control” as smo

[0308] Participant "Non-RT RIC" as NRTRIC

[0309] End box

[0310] Box "O-RAN Nodes" #lightpink

[0311] Participant"Near-RT RIC"as RTRIC

[0312] Participant"E2-Nodes"as E2NODES

[0313] Participant"O-RUs"as ORUs

[0314] End box

[0315] autonumber 1.1

[0316] Group data collection

[0317] alt via O1

[0318] smo->E2NODES:< <o1>>Energy-saving data collection request

[0319] E2NODES->ORUs:< <fh>>Data collection request

[0320] Else via OFH-MP

[0321] smo->ORUs:< <ofh-mp>>Data collection request

[0322] end

[0323] autonumber 2.1

[0324] alt Via O1

[0325] ORUs->E2NODES:< <fh>>Measurement data collection

[0326] E2NODES->smo:< <o1>>Energy-saving measurement collection

[0327] Else via OFH-MP

[0328] ORUs->smo:< <fh>>Measurement data collection

[0329] E2NODES->smo:< <o1>>Energy-saving measurement collection

[0330] End

[0331] autonumber 3

[0332] smo->NRTRIC:< <o1>>Data Retrieval

[0333] end

[0334] autonumber 4.1

[0335] group AI / ML workflow

[0336] NRTRIC->NRTRIC: AI / ML Model Training

[0337] NRTRIC->NRTRIC: Monitoring and Analysis of Efficiency and Energy Consumption (E2 Node and O-RU)

[0338] NRTRIC->RTRIC:< <o1> >or< <o2>>Deploy AI / ML models

[0339] end

[0340] autonumber 5.1

[0341] Group optimization triggers and policies

[0342] alt via O1

[0343] smo->RTRIC:< <o1>>Optimize Trigger / Target

[0344] else via A1

[0345] NRTRIC-->RTRIC:< <a1>>Intention-based Strategy

[0346] end

[0347] autonumber 6.1

[0348] Group Actor Data Collection and Decision Making

[0349] RTRIC->E2NODES:< <e2>>Energy-saving data collection request

[0350] E2NODES->ORUs:< <fh>>Energy-saving data collection request

[0351] ORUs->E2NODES:< <fh>>Energy-saving measurement data collection

[0352] E2NODES->RTRIC:< <e2>>Energy-saving measurement data collection

[0353] RTRIC->RTRIC: AI / ML model inference

[0354] RTRIC->E2NODES: < <e2>>Advanced Sleep Mode and Associated Energy Saving Methods

[0355] E2 NODES->ORUs:< <fh>>Updated O-RU Configuration

[0356] autonumber 6.1

[0357] Group AI / ML Workflow

[0358] NRTRIC->NRTRIC: Performance Analysis of AI / ML Models (including possible actions such as fallback, retraining)

[0359] NRTRIC->RTRIC:< <o1> >or< <o2>>Update AI / ML Model

[0360] end

[0361] @enduml

[0362] Figure 7.1.1-1: Advanced Sleep Mode Feature Flow

[0363] 7.1.4.2 O-RAN Entity Roles

[0364] 1) SMO (including non-RT RIC)

[0365] Collect necessary cell configurations, performance metrics, and measurement reports (e.g., cell load and traffic-related information, EE / EC measurement reports, and geographical location information, etc.) from E2 nodes and O-RUs to train an AI / ML model to assist in EE / ES functions.

[0366] Trigger and execute EE / ES AI / ML model training / retraining.

[0367] Analyze the data received from E2 nodes and O-RUs to trigger advanced sleep mode features

[0368] Provide optimization triggers, optimization objectives, and A1 policies (e.g., enabling traffic shaping to extend the sleep mode at 50% peak power consumption) to the near-RT RIC via the O1 or A1 interface

[0369] 2) near-RT RIC

[0370] Collect necessary cell configurations, performance metrics, and measurement reports (e.g., cell load-related and traffic information, EE / EC measurement reports) from E2 nodes and O-RUs.

[0371] Receive the EE / ES AI / ML model via O1 for deployment.

[0372] Receive EE / ES-related configuration management via the O1 interface and / or receive policies via the A1 interface for consideration during optimization.

[0373] Analyze the data received from E2 nodes and perform AI / ML model inference to determine the advanced sleep mode actions of EE / ES to be executed considering the optimization objectives / policies (e.g., traffic shaping for data aggregation in symbols and / or time slots, adjusting the broadcast intervals of RMSI and common channels, aligning the DRX cycles of UEs in the cell).

[0374] Provide policies and / or required information via the E2 interface to trigger operations for EE / ES optimization.

[0375] 3) E2 node

[0376] Report necessary cell configurations, performance metrics, and measurement reports (e.g., cell load-related and traffic information, EE / EC measurement reports) and the capabilities of the advanced sleep mode to the SMO via the O1 interface and to the near-RT RIC via the E2 or O1 interface.

[0377] Execute the advanced sleep mode on the O-RU based on the policies or recommendations of the near-RT RIC.

[0378] Perform operations such as shaping to achieve data aggregation in symbols or time slots, adjusting the RMSI broadcast interval and common channels, aligning the DRX cycles of UEs in the cell, and increasing the frequency and depth of O-RU sleep using multi-carrier-based energy-saving methods.

[0379] 4) O-RU

[0380] Report advanced sleep mode-related capability information to the O-DU via the M-plane.

[0381] The O-DU indicates the transition from the active mode to the desired sleep mode via the CUS-plane and reports power consumption and sleep state-related information to the O-DU or the SMO via the M-plane.

[0382] 7.1.4.3 Input / Output Data Requirements

[0383] 7.1.4.3.1 Overview

[0384] Input Data

[0385] 1) SMO and E2 Nodes

[0386] Load statistics for each cell and each carrier, such as the number of active users, the average number of RRC connections, the average number of scheduled active users per TTI, PRB utilization, DL / UL cell / user throughput, PMI / CSI reports.

[0387] Delay statistics for each cell (if URLLC slices are involved, the delay is used in EE-defined TS28.554).

[0388] The capabilities of the O-DU related to the advanced sleep mode.

[0389] 2) O-RU

[0390] Power consumption metrics: average total power consumption and power consumption per carrier.

[0391] Power consumption for each sleep mode.

[0392] O-RU information on supported advanced sleep modes and transition times from sleep to active (site / O-RU input power required for certain EE KPIs).

[0393] Output Data

[0394] 1) Non-RT RIC to Near-RT RIC

[0395] O1 configuration (i.e., ES optimization trigger / target) or

[0396] A1 Execution policy for advanced sleep mode based on operator strategy.

[0397] 2) Near-RT RIC to E2 node

[0398] Policies and guidelines on activating traffic shaping to minimize active symbols and time slots (TTI)

[0399] Policies and guidelines on performing dormant sleep (due to expected latency higher than 10 ms)

[0400] Policies and guidelines on the configuration of common channels and RMSI.

[0401] 3) E2 node to O-RU

[0402] a. Appropriate sleep mode execution commands on the CUS-plane

[0403] 7.2 Impact analysis on the O-RAN working group

[0404] 7.3 Relationship with 3GPP specifications and its impact

[0405] 7.4 Gain analysis

[0406] 7.5 Feasibility analysis

[0407] 7.5.1 Impact of advanced sleep mode on continuous operation

[0408] ASM limited to the symbol level is expected to have no significant impact on user performance. However, longer sleep modes involving shutting down more components or reducing their activity for a longer time may have a greater impact on user performance as they can lead to a degradation of service quality such as increased latency or reduced data transfer rate.

[0409] 7.5.2 Impact on coverage

[0410] If the O-RU executes the deep sleep mode by adjusting the SSB period of NR to exceed 20 ms, the UE may not be able to connect to the gNB due to the lack of SSB measurement, so the coverage of this area may be affected. However, when there are multiple carriers, this problem can be solved by appropriately configuring the sparse synchronization raster.

[0411] 7.5.3 Impact and relationship on vendor-specific scheduling and beamforming algorithms

[0412] The advanced sleep mode may affect cell and user performance.

[0413] Handling such events most efficiently depends on the proprietary scheduling algorithm. Scheduling (e.g., user selection, resource allocation), adaptive SU-MIMO and MU-MIMO (e.g., MIMO mode, spatial streams, and layers), and scheduling of common and shared channels will be regulated by the base station according to the policies set by the near RT RIC.

[0414] 7.5.4 Limited O-RU / O-DU capabilities

[0415] There may be limitations in the O-RU and O-DU in implementing the sleep mode function. Even if the O-RU supports the ASM feature, due to the overall specification framework, it is unlikely to support all ASMs. This may introduce multi-vendor interoperability issues.

[0416] Figure 7.1.3.1: Data aggregation in the above symbols and Figure 10 are consistent.

[0417] Figure 7.1.3-2: Data aggregation in the above time slots and Figure 11 are consistent.

[0418] Figure 7.1.1-1: The above advanced sleep mode feature process and Figure 12A , Figure 12B and Figures 13 to 15 are consistent.

[0419] The above disclosure provides illustration and description, but is not intended to be exhaustive or limit the implementation to the exact form disclosed. Modifications and variations are possible according to the above disclosure, or can be obtained from the practice of the implementation.

[0420] Some embodiments may relate to systems, methods, and / or computer-readable media at any possible level of integrated technical detail. Additionally, one or more of the above 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 (multiple) computer-readable non-transitory storage media having computer-readable program instructions thereon for causing the processor to execute operations.

[0421] A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium can be, by way of example and not limitation, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer-readable storage medium includes: a portable computer floppy disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device on which instructions are recorded (such as a punch card or raised structures in grooves), and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0422] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a respective computing / processing device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network), or to an external computer or external storage device. The network can include copper transmission cables, optical transmission fibers, wireless transmission, 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 forwards the computer-readable program instructions for storage in a computer-readable storage medium within the respective computing / processing device.

[0423] The computer-readable program code / instructions for performing the operations can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, configuration data for an integrated circuit system, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages (such as Smalltalk, C++, etc.) and procedural programming languages (such as the "C" programming language or similar programming languages). The computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any type of network connection, including a local area network (LAN) or a wide area network (WAN), or the connection to an external computer can be made (e.g., using an Internet service provider over the Internet). In some embodiments, an electronic circuit system (including, for example, a programmable logic circuit system, a field programmable gate array (FPGA), or a programmable logic array (PLA)) can execute the computer-readable program instructions by utilizing the state information of the computer-readable program instructions to personalize the electronic circuit system, thereby performing various aspects or operations.

[0424] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions executed via the processor of the computer or other programmable data processing apparatus create a component for implementing the functions / actions specified in the flowchart and / or block diagram blocks. These computer-readable program instructions can also be stored in a computer-readable storage medium, which can direct a computer, a programmable data processing apparatus, and / or other devices to work in a particular manner, such that the computer-readable storage medium in which the instructions are stored includes an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in the flowchart and / or block diagram blocks.

[0425] The computer-readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be executed on the computer, other programmable apparatus, or other devices, thereby producing a computer-implemented process, such that the instructions executed on the computer, other programmable apparatus, or other devices implement the functions / actions specified in the flowchart and / or block diagram blocks.

[0426] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer-readable media according to various embodiments. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of (one or more) microservices, instructions, which include one or more executable instructions for implementing the specified logical function(s). Compared with what is shown in the figures, the method, computer system, and computer-readable media may include more blocks, fewer blocks, different blocks, or blocks arranged differently. In some alternative implementations, the functions described in the blocks may not occur in the order shown in the figures. For example, in fact, two consecutive blocks shown may be executed simultaneously or substantially simultaneously, or these blocks may sometimes be executed in the reverse order, depending on the functions involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can be implemented by a system based on dedicated hardware that performs the specified functions or actions or a combination of dedicated hardware and computer instructions.

[0427] It is clear that the systems and / or methods described herein can 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 does not limit these implementations. Therefore, the operation and behavior of these systems and / or methods are described herein without reference to specific software code. It should be understood that software and hardware can be designed to implement these systems and / or methods based on the description herein.

[0428] Various additional corresponding aspects and features of the embodiments of the present disclosure may be defined by the following clauses:

[0429] Clause [1] A system for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN), the system comprising: a near real-time Radio Access Network (RAN) Intelligent Controller (nRT-RIC) and a Service Management and Orchestration (SMO) framework, the SMO framework comprising: a non-real-time Radio Access Network (RAN) Intelligent Controller (NRT-RIC), wherein the system is configured to: collect measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model by the SMO framework; train the AI / ML model by the NRT-RIC based on the collected measurement data and deploy the AI / ML model in the nRT-RIC; activate the trained AI / ML model in the nRT-RIC by the SMO framework; monitor energy optimization data of AI / ML model inference from an Open Radio Unit (O-RU) by the NRT-RIC via an E2 node; activate at least one Advanced Sleep Mode (ASM) in the nRT-RIC by the SMO framework; collect data for temporarily deactivating one or more O-RU components from the O-RU by the nRT-RIC via the E2 node based on the activation of at least one ASM; evaluate the collected data for temporarily deactivating one or more O-RU components by the nRT-RIC based on the activated AI / ML model and at least one ASM; request to initiate at least one ASM to the O-RU by the nRT-RIC via the E2 node based on the evaluation; and implement at least one ASM by the O-RU based on the ASM initiation request.

[0430] Clause [2] The system according to clause [1], wherein the system is configured to collect data for temporarily deactivating one or more O-RU components based on the activation of at least one ASM by: sending an energy-saving data collection request from the nRT-RIC to the E2 node via the E2 interface; receiving the energy-saving data collection request at the E2 node from the nRT-RIC; collecting data for temporarily deactivating one or more O-RU components from the O-RU by the E2 node via an Open FH M-plane interface; and sending the collected data for temporarily deactivating one or more O-RU components to the nRT-RIC by the E2 node via the E2 interface.

[0431] Clause [3] The system according to clause [1 or 2], wherein the system is configured to evaluate the collected data for temporarily deactivating one or more O-RU components by: receiving, by the nRT-RIC, from the E2 node, the collected data for temporarily deactivating one or more O-RU components; applying, by the nRT-RIC, AI / ML model inference based on the collected data for temporarily deactivating one or more O-RU components; generating, by the nRT-RIC, at least one E2 control command in the E2 control commands based on the AI / ML model inference, the at least one E2 control command being for requesting to initiate at least one ASM to an E2 node compliant with the capabilities of the O-RU; and sending, by the nRT-RIC, the at least one E2 control command in the E2 control commands to the E2 node.

[0432] Clause [4] The system according to clause [1 or 2], wherein the system is configured to evaluate the collected data for temporarily deactivating one or more O-RU components by: receiving, by the nRT-RIC, from the E2 node, the collected data for temporarily deactivating one or more O-RU components; applying, by the nRT-RIC, AI / ML model inference based on the collected data for temporarily deactivating one or more O-RU components; generating, by the nRT-RIC, at least one E2 policy command in the E2 policy commands for energy saving (ES) based on the AI / ML model inference, the at least one E2 policy command instructing an E2 node compliant with the capabilities of the O-RU to initiate at least one ASM; and sending, by the nRT-RIC, the at least one E2 policy command to the E2 node.

[0433] Clause [5] The system according to any one of clauses [1 to 4], wherein the system may further be configured to: receive, by the NRT-RIC via the SMO framework, feedback including a performance analysis of the AI / ML model based on implementation; analyze, by the NRT-RIC, the performance of the AI / ML model in the nRT-RIC; determine, by the NRT-RIC, that at least one predetermined performance target is not achieved based on the performance of the AI / ML model; and initiate, by the NRT-RIC, a fallback mechanism related to at least one predetermined performance target.

[0434] Clause [6] The system according to any one of clauses [1 to 5], wherein the system is configured to implement at least one ASM by: scheduling, by the E2 node or the O-RU, at least one symbol based on the capabilities of the O-RU to minimize the number of symbols in the time domain, wherein the E2 node or the O-RU is configured to perform the scheduling by: aggregating at least one symbol from the time domain to the frequency domain to extend the deactivation period of one or more O-RU components, wherein the at least one aggregated symbol is at least one of a physical downlink shared channel PDSCH symbol and a physical downlink control channel PDCCH symbol.

[0435] Clause [7] A system according to any one of Clauses [1 to 5], wherein the system is configured to implement at least one ASM by: scheduling, by an E2 node or an O-RU, at least one time slot based on the capabilities of the O-RU to minimize the number of time slots in the time domain, wherein the E2 node or the O-RU is configured to perform the scheduling by: aggregating at least one time slot from the time domain to the frequency domain to extend the deactivation period of one or more O-RU components, wherein the at least one aggregated time slot is at least one of the following: a Synchronization Signal Block - Master Information Block SSB-MIB time slot, a System Information Block type 1 SIB1 time slot, an SI time slot, a paging frame time slot, and a Physical Downlink Shared Channel PDSCH time slot.

[0436] Clause [8] A method for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN), the method comprising: collecting, by a Service Management and Orchestration (SMO) framework, measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model; training, by a Non-Real-Time Radio Access Network (RAN) Intelligent Controller (NRT-RIC) based on the collected measurement data, the AI / ML model and deploying the AI / ML model in a Near-Real-Time Radio Access Network Intelligent Controller (nRT-RIC); activating, by the SMO framework, the trained AI / ML model in the nRT-RIC; monitoring, by the NRT-RIC via an E2 node, energy optimization data from an Open Radio Unit (O-RU) for AI / ML model inference; activating, by the SMO framework, at least one Advanced Sleep Mode (ASM) in the nRT-RIC; collecting, based on the activation of the at least one ASM, by the nRT-RIC via the E2 node, data for temporarily deactivating one or more O-RU components from the O-RU; evaluating, by the nRT-RIC based on the activated AI / ML model and the at least one ASM, the collected data for temporarily deactivating one or more O-RU components; requesting, based on the evaluation, by the nRT-RIC via the E2 node, to initiate at least one ASM to the O-RU; and implementing, by the O-RU based on the ASM initiation request, at least one ASM.

[0437] Clause [9] The method according to Clause [8], wherein collecting data for temporarily deactivating one or more O-RU components based on the activation of the at least one ASM may include: sending, by the nRT-RIC via an E2 interface, an energy-saving data collection request to the E2 node; receiving, by the E2 node, the energy-saving data collection request from the nRT-RIC; collecting, by the E2 node via an Open FH M-plane interface, data for temporarily deactivating one or more O-RU components from the O-RU; and sending, by the E2 node via the E2 interface, the collected data for temporarily deactivating one or more O-RU components to the nRT-RIC.

[0438] Clause

[10] The method according to clause [8 or 9], wherein evaluating the data collected for temporarily deactivating one or more O-RU components may include: receiving, by the nRT-RIC, from the E2 node, the data collected for temporarily deactivating one or more O-RU components; applying, by the nRT-RIC, AI / ML model inference based on the data collected for temporarily deactivating one or more O-RU components; generating, by the nRT-RIC, at least one E2 control command in the E2 control commands based on the AI / ML model inference, the at least one E2 control command being for requesting to initiate at least one ASM to an E2 node compliant with the capabilities of the O-RU; and sending, by the nRT-RIC, the at least one E2 control command in the E2 control commands to the E2 node.

[0439] Clause

[11] The method according to clause [8 or 9], wherein evaluating the data collected for temporarily deactivating one or more O-RU components may include: receiving, by the nRT-RIC, from the E2 node, the data collected for temporarily deactivating one or more O-RU components; applying, by the nRT-RIC, AI / ML model inference based on the data collected for temporarily deactivating one or more O-RU components; generating, by the nRT-RIC, at least one E2 policy command in the E2 policy commands for energy saving (ES) based on the AI / ML model inference, the at least one E2 policy command instructing an E2 node compliant with the capabilities of the O-RU to initiate at least one ASM; and sending, by the nRT-RIC, the at least one E2 policy command to the E2 node.

[0440] Clause

[12] The method according to any one of clauses [8 to 11], the method may include: receiving, by the NRT-RIC via the SMO framework, based on the implementation, feedback including a performance analysis of the AI / ML model; analyzing, by the NRT-RIC, the performance of the AI / ML model in the nRT-RIC; determining, by the NRT-RIC, based on the performance of the AI / ML model, that at least one predetermined performance target is not achieved; and initiating, by the NRT-RIC, a fallback mechanism related to at least one predetermined performance target.

[0441] Clause

[13] The method according to any one of clauses [8 to 12], wherein implementing at least one ASM may include: scheduling, by the E2 node or the O-RU, at least one symbol based on the capabilities of the O-RU to minimize the number of symbols in the time domain, wherein the scheduling may include: aggregating at least one symbol from the time domain to the frequency domain to extend the deactivation period of one or more O-RU components, wherein the at least one aggregated symbol is at least one of a physical downlink shared channel PDSCH symbol and a physical downlink control channel PDCCH symbol.

[0442] Clause

[14] The method according to any one of Clauses [8 to 12], wherein implementing at least one ASM by the E2 node and the O-RU may include: scheduling at least one time slot by the E2 node or the O-RU based on the capabilities of the O-RU to minimize the number of time slots in the time domain, wherein the scheduling may include: aggregating at least one time slot from the time domain to the frequency domain to extend the deactivation period of one or more O-RU components, wherein the at least one aggregated time slot is at least one of the following: Synchronization Signal Block - Master Information Block SSB-MIB time slot, System Information Block type 1 SIB1 time slot, SI time slot, Paging Frame time slot, and Physical Downlink Channel PDSCH time slot.

[0443] Clause

[15] : A non-transitory computer-readable recording medium having recorded thereon instructions executable by at least one processor, the processor being configured to implement a method for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN), the method including: collecting measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model by a Service Management and Orchestration (SMO) framework; training the AI / ML model by a Non-Real-Time Radio Access Network (RAN) Intelligent Controller (NRT-RIC) based on the collected measurement data and deploying the AI / ML model in a Near Real-Time Radio Access Network Intelligent Controller (nRT-RIC); activating the trained AI / ML model in the nRT-RIC by the SMO framework; monitoring, by the NRT-RIC via an E2 node, energy optimization data from an Open Radio Unit (O-RU) for AI / ML model inference; activating at least one Advanced Sleep Mode (ASM) in the nRT-RIC by the SMO framework; collecting, based on the activation of the at least one ASM, by the nRT-RIC via the E2 node, data for temporarily deactivating one or more O-RU components from the O-RU; evaluating, based on the activated AI / ML model and the at least one ASM, the collected data for temporarily deactivating one or more O-RU components by the nRT-RIC; requesting, based on the evaluation, by the nRT-RIC via the E2 node, to initiate at least one ASM to the O-RU; and implementing at least one ASM by the O-RU based on the ASM initiation request.

[0444] Clause

[16] The non-transitory computer-readable recording medium according to Clause

[15] , wherein collecting data for temporarily deactivating one or more O-RU components based on the activation of at least one ASM may include: the nRT-RIC sending an energy-saving data collection request to the E2 node via the E2 interface; the E2 node receiving the energy-saving data collection request from the nRT-RIC; the E2 node collecting data for temporarily deactivating one or more O-RU components from the O-RU via the open FH M-plane interface; and the E2 node sending the collected data for temporarily deactivating one or more O-RU components to the nRT-RIC via the E2 interface.

[0445] Clause

[17] The non-transitory computer-readable recording medium according to Clause [15 or 16], wherein evaluating the collected data for temporarily deactivating one or more O-RU components may include: the nRT-RIC receiving the collected data for temporarily deactivating one or more O-RU components from the E2 node; the nRT-RIC applying AI / ML model inference based on the collected data for temporarily deactivating one or more O-RU components; the nRT-RIC generating at least one E2 control command in the E2 control command based on the AI / ML model inference, the at least one E2 control command being used to request to initiate at least one ASM to an E2 node conforming to the capabilities of the O-RU; the nRT-RIC generating at least one E2 policy command in the E2 policy command for energy saving (ES) based on the AI / ML model inference, the at least one E2 policy command instructing the E2 node conforming to the capabilities of the O-RU to initiate at least one ASM; and the nRT-RIC sending at least one of the E2 control command and / or the E2 policy command to the E2 node.

[0446] Clause

[18] The non-transitory computer-readable recording medium according to Clause [15 or 17], the method may include: based on implementation, the NRT-RIC receiving feedback including the performance analysis of the AI / ML model via the SMO framework; the NRT-RIC analyzing the performance of the AI / ML model in the nRT-RIC; the NRT-RIC determining that at least one predetermined performance target is not achieved based on the performance of the AI / ML model; and the NRT-RIC initiating a fallback mechanism related to at least one predetermined performance target.

[0447] Clause

[19] A non-transitory computer-readable recording medium according to any one of Clauses [15 to 18], wherein implementing at least one ASM may include: scheduling at least one symbol by an E2 node or an O-RU based on the capabilities of the O-RU to minimize the number of symbols in the time domain, wherein the scheduling may include: aggregating at least one symbol from the time domain to the frequency domain to extend the deactivation period of one or more O-RU components, wherein the at least one aggregated symbol is at least one of a physical downlink shared channel (PDSCH) symbol and a physical downlink control channel (PDCCH) symbol.

[0448] Clause

[20] A non-transitory computer-readable recording medium according to any one of Clauses [15 to 18], wherein implementing at least one ASM may include: scheduling at least one time slot by an E2 node or an O-RU based on the capabilities of the O-RU to minimize the number of time slots in the time domain, wherein the scheduling may include: aggregating at least one time slot from the time domain to the frequency domain to extend the deactivation period of one or more O-RU components, wherein the at least one aggregated time slot is at least one of the following: a synchronization signal block - master information block (SSB-MIB) time slot, a system information block type 1 (SIB1) time slot, a SI time slot, a paging frame time slot, and a physical downlink shared channel (PDSCH) time slot. < / o1> < / fh> < / fh> < / fh> < / o1> < / fh> < / fh> < / fh>

Claims

1. A system for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN), the system comprising: a Near Real-Time Radio Access Network (RAN) Intelligent Controller (nRT-RIC) and a Service Management and Orchestration (SMO) framework, the SMO framework including: a Non-Real-Time Radio Access Network (RAN) Intelligent Controller (NRT-RIC), wherein the system is configured to: collect measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model by the SMO framework; train the AI / ML model by the NRT-RIC based on the collected measurement data and deploy the AI / ML model in the nRT-RIC; activate the trained AI / ML model in the nRT-RIC by the SMO framework; monitor energy optimization data of AI / ML model inference from an Open Radio Unit (O-RU) by the NRT-RIC via an E2 node; activate at least one Advanced Sleep Mode (ASM) in the nRT-RIC by the SMO framework; collect data for temporarily deactivating one or more O-RU components from the O-RU by the nRT-RIC via the E2 node based on the activation of the at least one ASM; evaluate the collected data for temporarily deactivating one or more O-RU components by the nRT-RIC based on the activated AI / ML model and the at least one ASM; request to initiate the at least one ASM to the O-RU by the nRT-RIC via the E2 node based on the evaluation; and implement the at least one ASM by the O-RU based on the ASM initiation request.

2. The system according to claim 1, wherein the system is configured to collect the data for temporarily deactivating the one or more O-RU components based on the activation of the at least one ASM by: sending an energy-saving data collection request from the nRT-RIC to the E2 node via an E2 interface; receiving the energy-saving data collection request at the E2 node from the nRT-RIC; collecting the data for temporarily deactivating the one or more O-RU components from the O-RU by the E2 node via an Open FH M-plane interface; and sending the collected data for temporarily deactivating the one or more O-RU components to the nRT-RIC by the E2 node via the E2 interface.

3. The system according to claim 1, wherein the system is configured to evaluate the collected data for temporarily deactivating the one or more O-RU components by: receiving the collected data for temporarily deactivating the one or more O-RU components at the nRT-RIC from the E2 node; applying AI / ML model inference by the nRT-RIC based on the collected data for temporarily deactivating the one or more O-RU components; Based on the AI / ML model inference, at least one E2 control command is generated by the nRT-RIC in the E2 control commands, and the at least one E2 control command is used to request to initiate the at least one ASM to the E2 node that conforms to the capabilities of the O-RU; and the at least one E2 control command in the E2 control commands is sent by the nRT-RIC to the E2 node.

4. The system according to claim 1, wherein the system is configured to evaluate the collected data for temporarily deactivating the one or more O-RU components by: receiving, by the nRT-RIC from the E2 node, the collected data for temporarily deactivating the one or more O-RU components; applying, by the nRT-RIC, AI / ML model inference based on the collected data for temporarily deactivating the one or more O-RU components; generating, by the nRT-RIC based on the AI / ML model inference, at least one E2 policy command for energy saving (ES) in the E2 policy commands, and the at least one E2 policy command instructs the E2 node that conforms to the capabilities of the O-RU to initiate the at least one ASM; and sending, by the nRT-RIC, the at least one E2 policy command to the E2 node.

5. The system according to claim 1, wherein the system is further configured to: receive, by the NRT-RIC via the SMO framework based on the implementation, feedback including a performance analysis of the AI / ML model; analyze, by the NRT-RIC, the performance of the AI / ML model in the nRT-RIC; determine, by the NRT-RIC based on the performance of the AI / ML model, that at least one predetermined performance target is not achieved; and initiate, by the NRT-RIC, a fallback mechanism related to the at least one predetermined performance target.

6. The system according to claim 1, wherein the system is configured to implement the at least one ASM by: scheduling, by the E2 node or the O-RU based on the capabilities of the O-RU, at least one symbol to minimize the number of symbols in the time domain, and the E2 node or the O-RU is configured to perform the scheduling by: converging the at least one symbol from the time domain to the frequency domain to extend the deactivation period of the one or more O-RU components, and the at least one symbol being converged is at least one of a physical downlink shared channel PDSCH symbol and a physical downlink control channel PDCCH symbol.

7. The system according to claim 1, wherein the system is configured to implement the at least one ASM by: scheduling, by the E2 node or the O-RU based on the capabilities of the O-RU, at least one time slot to minimize the number of time slots in the time domain, and the E2 node or the O-RU is configured to perform the scheduling by: Converge the at least one time slot from the time domain to the frequency domain to extend the deactivation period of the one or more O-RU components, where the at least one time slot to be converged is at least one of the following: Synchronization Signal Block-Master Information Block SSB-MIB time slot, System Information Block Type 1 SIB1 time slot, SI time slot, Paging Frame time slot, and Physical Downlink Shared Channel PDSCH time slot.

8. A method for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN), the method comprising: Collecting measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model by a Service Management and Orchestration (SMO) framework; Training the AI / ML model by a Non-Real-Time Radio Access Network (RAN) Intelligent Controller (NRT-RIC) based on the collected measurement data and deploying the AI / ML model in a Near-Real-Time Radio Access Network Intelligent Controller (nRT-RIC); Activating the trained AI / ML model in the nRT-RIC by the SMO framework; Monitoring, by the NRT-RIC via an E2 node, energy optimization data from AI / ML model inference of an Open Radio Unit (O-RU); Activating at least one Advanced Sleep Mode (ASM) in the nRT-RIC by the SMO framework; Based on the activation of the at least one ASM, collecting, by the nRT-RIC via the E2 node, data for temporarily deactivating one or more O-RU components from the O-RU; Evaluating, by the nRT-RIC, the collected data for temporarily deactivating one or more O-RU components based on the activated AI / ML model and the at least one ASM; Based on the evaluation, requesting, by the nRT-RIC via the E2 node, to initiate the at least one ASM to the O-RU; And Implementing, by the O-RU, the at least one ASM based on the ASM initiation request.

9. The method according to claim 8, wherein collecting the data for temporarily deactivating the one or more O-RU components based on the activation of the at least one ASM comprises: Sending, by the nRT-RIC via an E2 interface, an energy saving data collection request to the E2 node; Receiving, by the E2 node, the energy saving data collection request from the nRT-RIC; Collecting, by the E2 node via an Open FH M-plane interface, the data for temporarily deactivating the one or more O-RU components from the O-RU; And Sending, by the E2 node via the E2 interface, the collected data for temporarily deactivating the one or more O-RU components to the nRT-RIC.

10. The method according to claim 8, wherein evaluating the collected data for temporarily deactivating the one or more O-RU components comprises: Receiving, by the nRT-RIC, the collected data for temporarily deactivating the one or more O-RU components from the E2 node; Based on the collected data for temporarily deactivating the one or more O-RU components, the nRT-RIC applies AI / ML model inference; Based on the AI / ML model inference, the nRT-RIC generates at least one E2 control command in the E2 control commands, and the at least one E2 control command is used to request to initiate the at least one ASM to the E2 node that conforms to the capabilities of the O-RU; and The nRT-RIC sends the at least one E2 control command in the E2 control commands to the E2 node.

11. The method according to claim 8, wherein evaluating the collected data for temporarily deactivating the one or more O-RU components includes: The nRT-RIC receives from the E2 node the collected data for temporarily deactivating the one or more O-RU components; Based on the collected data for temporarily deactivating the one or more O-RU components, the nRT-RIC applies AI / ML model inference; Based on the AI / ML model inference, the nRT-RIC generates at least one E2 policy command in the E2 policy commands for energy saving (ES), and the at least one E2 policy command instructs the E2 node that conforms to the capabilities of the O-RU to initiate the at least one ASM; and The nRT-RIC sends the at least one E2 policy command to the E2 node.

12. The method according to claim 8, the method includes: Based on the implementation, the NRT-RIC receives, via the SMO framework, feedback including a performance analysis of the AI / ML model; The NRT-RIC analyzes the performance of the AI / ML model in the nRT-RIC; The NRT-RIC determines, based on the performance of the AI / ML model, that at least one predetermined performance target is not achieved; and The NRT-RIC initiates a fallback mechanism related to the at least one predetermined performance target.

13. The method according to claim 8, wherein implementing the at least one ASM includes: Based on the capabilities of the O-RU, the E2 node or the O-RU schedules at least one symbol to minimize the number of symbols in the time domain, and the scheduling includes: Aggregating the at least one symbol from the time domain to the frequency domain to extend the deactivation period of the one or more O-RU components, and the aggregated at least one symbol is at least one of a physical downlink shared channel PDSCH symbol and a physical downlink control channel PDCCH symbol.

14. The method according to claim 8, wherein implementing the at least one ASM by the E2 node and the O-RU includes: Based on the capabilities of the O-RU, the E2 node or the O-RU schedules at least one time slot to minimize the number of time slots in the time domain, and the scheduling includes: Aggregate the at least one time slot from the time domain to the frequency domain to extend the deactivation period of the one or more O-RU components, where the aggregated at least one time slot is at least one of the following: Synchronization Signal Block-Master Information Block SSB-MIB time slot, System Information Block type 1 SIB1 time slot, SI time slot, Paging Frame time slot, and Physical Downlink Shared Channel PDSCH time slot.

15. A non-transitory computer-readable recording medium having recorded thereon instructions executable by at least one processor, the at least one processor being configured to implement a method for implementing an advanced sleep mode in an Open Radio Access Network (O-RAN), the method comprising: Collect measurement data for training an Artificial Intelligence / Machine Learning (AI / ML) model by a Service Management and Orchestration (SMO) framework; Based on the collected measurement data, train an AI / ML model by a Non-Real-Time Radio Access Network (RAN) Intelligent Controller (NRT-RIC) and deploy the AI / ML model in a Near-Real-Time Radio Access Network Intelligent Controller (nRT-RIC); Activate the trained AI / ML model in the nRT-RIC by the SMO framework; Monitor, by the NRT-RIC via an E2 node, energy optimization data from AI / ML model inference of an Open Radio Unit (O-RU); Activate at least one Advanced Sleep Mode (ASM) in the nRT-RIC by the SMO framework; Based on the activation of the at least one ASM, collect, by the nRT-RIC via the E2 node, data for temporarily deactivating one or more O-RU components from the O-RU; Evaluate, by the nRT-RIC, the collected data for temporarily deactivating one or more O-RU components based on the activated AI / ML model and the at least one ASM; Based on the evaluation, request, by the nRT-RIC via the E2 node, to initiate the at least one ASM to the O-RU; And Implement the at least one ASM by the O-RU based on the ASM initiation request.

16. The non-transitory computer-readable recording medium according to claim 15, wherein collecting the data for temporarily deactivating the one or more O-RU components based on the activation of the at least one ASM comprises: Send an energy-saving data collection request from the nRT-RIC to the E2 node via an E2 interface; Receive the energy-saving data collection request at the E2 node from the nRT-RIC; Collect, by the E2 node via an Open FH M-plane interface, the data for temporarily deactivating the one or more O-RU components from the O-RU; And Send, by the E2 node via the E2 interface, the collected data for temporarily deactivating the one or more O-RU components to the nRT-RIC.

17. The non-transitory computer-readable recording medium according to claim 15, wherein evaluating the collected data for temporarily deactivating the one or more O-RU components includes: receiving, by the nRT-RIC from the E2 node, the collected data for temporarily deactivating the one or more O-RU components; applying, by the nRT-RIC, AI / ML model inference based on the collected data for temporarily deactivating the one or more O-RU components; generating, by the nRT-RIC based on the AI / ML model inference, at least one E2 control command in the E2 control commands, the at least one E2 control command being used to request initiating the at least one ASM to the E2 node conforming to the capabilities of the O-RU; generating, by the nRT-RIC based on the AI / ML model inference, at least one E2 policy command in the E2 policy commands for energy saving (ES), the at least one E2 policy command guiding the E2 node conforming to the capabilities of the O-RU to initiate the at least one ASM; and sending, by the nRT-RIC to the E2 node, at least one of the E2 control command and / or the E2 policy command.

18. The non-transitory computer-readable recording medium according to claim 15, the method includes: receiving, by the NRT-RIC via the SMO framework based on the implementation, feedback including a performance analysis of the AI / ML model; analyzing, by the NRT-RIC, the performance of the AI / ML model in the nRT-RIC; determining, by the NRT-RIC based on the performance of the AI / ML model, that at least one predetermined performance target is not achieved; and initiating, by the NRT-RIC, a fallback mechanism related to the at least one predetermined performance target.

19. The non-transitory computer-readable recording medium according to claim 15, wherein implementing the at least one ASM includes: scheduling, by the E2 node or the O-RU based on the capabilities of the O-RU, at least one symbol to minimize the number of symbols in the time domain, wherein the scheduling includes: converging the at least one symbol from the time domain to the frequency domain to extend the deactivation period of the one or more O-RU components, wherein the at least one converged symbol is at least one of a physical downlink shared channel PDSCH symbol and a physical downlink control channel PDCCH symbol.

20. The non-transitory computer-readable recording medium according to claim 15, wherein implementing the at least one ASM includes: scheduling, by the E2 node or the O-RU based on the capabilities of the O-RU, at least one time slot to minimize the number of time slots in the time domain, wherein the scheduling includes: Aggregate the at least one time slot from the time domain to the frequency domain to extend the deactivation period of the one or more O-RU components, wherein the at least one aggregated time slot is at least one of the following: Synchronization Signal Block-Master Information Block SSB-MIB time slot, System Information Block type 1 SIB1 time slot, SI time slot, paging frame time slot, and Physical Downlink Shared Channel PDSCH time slot.

Images