Service profiling and quality of service management at orchestrator to support scheduling of compute services in wireless communication systems
By introducing an orchestrator node into the wireless communication system to manage the resource allocation and communication paths of computing tasks, the problem of inefficient offloading of computationally intensive tasks is solved, and efficient offloading of computing tasks and optimization of communication paths are achieved.
Patent Information
- Application Number
- CN202580025901.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-04-01
- Filing Date
- 2025-04-01
- Publication Date
- 2026-11-10
AI Technical Summary
Existing wireless communication systems struggle to effectively manage the performance requirements of computing tasks and the limitations of communication paths when handling computational activity offloading, resulting in low efficiency in offloading computationally intensive tasks.
By introducing an orchestrator node into the wireless communication system, service profiles are obtained and network domain-specific configuration information is generated. This information is then sent to multiple nodes to achieve network domain-specific operations, thereby optimizing resource allocation and communication path management for computing tasks.
It achieves efficient offloading of computationally intensive tasks, meets computing performance requirements, optimizes the use of communication paths, and improves the overall efficiency and reliability of the system.
Smart Images

Figure CN123077178A_ABST
Abstract
Description
[0001] Cross-referencing
[0002] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 572,390, entitled “Service Profile and Quality of Service Management at the Orchestrator to Support Scheduling of Computational Services in a Wireless Communications System,” filed April 1, 2024, the entire contents of which are hereby expressly incorporated by reference. Technical Field
[0003] This disclosure generally relates to wireless communications, and more specifically, to techniques for processing services in wireless communication systems that support offloading computing activities from client devices to one or more computing nodes. Background Technology
[0004] The statements in this section provide only background information in relation to this disclosure and may not constitute prior art.
[0005] Wireless communication systems are widely deployed to provide a variety of telecommunications services, such as telephone, video, data, messaging, and broadcasting. Typical wireless communication systems employ various multiple access technologies to support communication with multiple users by sharing available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single-carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.
[0006] These multiple access technologies have been adopted in various telecommunications standards to provide a common protocol, enabling different wireless devices to communicate at the city, national, regional, and even global levels. An example of a telecommunications standard is 5G New Radio (NR). 5G NR is part of the ongoing evolution of mobile broadband driven by the Third Generation Partnership Project (3GPP) to meet new requirements related to latency, reliability, security, scalability (e.g., related to the Internet of Things (IoT),) and other requirements. Some aspects of 5G NR can be based on the 4G Long Term Evolution (LTE) standard. There is a need for further improvements to 5G NR technology. These improvements can also be applied to other multiple access technologies and telecommunications standards that adopt them. Summary of the Invention
[0007] The following content presents one or more aspects in a simplified form to provide a basic understanding of these aspects. This summary is not a comprehensive overview of all conceived aspects, nor is it intended to identify key or essential elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present certain concepts of one or more aspects in a simplified form as a prelude to a more detailed description thereafter.
[0008] In one aspect of this disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a device acting as a first node in a communication system comprising multiple nodes distributed across at least one network domain. The first node obtains a service profile of a service. The service profile may define the performance requirements of the service. The first node generates network domain-specific configuration information based on the service profile. The first node sends the network domain-specific configuration information to a second node among the multiple nodes to implement network domain-specific operations for the service. The network domain-specific operations are related to resource allocation for the service.
[0009] To achieve the foregoing and related objectives, one or more aspects include the features described in detail below and specifically pointed out in the claims. The following description and accompanying drawings illustrate certain exemplary features of one or more aspects. However, these features only indicate a portion of the various aspects' principles that may be employed, and this description is intended to encompass all such aspects and their equivalents. Attached Figure Description
[0010] Figure 1 This is a schematic diagram illustrating an example wireless communication system and access network.
[0011] Figure 2 This is a schematic diagram illustrating communication between a base station and a user equipment (UE) in the access network.
[0012] Figure 3 Example of a distributed access network's logical architecture.
[0013] Figure 4 Example of a distributed access network physical architecture.
[0014] Figure 5 This is a schematic diagram of a downlink (DL) centered time slot.
[0015] Figure 6 This is a schematic diagram with the uplink (UL) as the center time slot.
[0016] Figure 7 A schematic diagram illustrating the interaction between nodes in a system that supports computational unloading.
[0017] Figure 8 A schematic diagram of a system that supports compute offloading and contains multiple compute nodes in different locations within the system.
[0018] Figure 9 This is a flowchart illustrating the process of unloading computing tasks to a computing node.
[0019] Figure 10 This diagram illustrates the interactions between client devices, orchestrators, and compute nodes for task offloading and performance monitoring.
[0020] Figure 11 This is a schematic diagram illustrating the process of establishing a bearer between a client device and a computing node in the network, initiated by the orchestrator.
[0021] Figure 12 It provides an interactive diagram of the interactions between client devices, orchestrators, compute nodes, and base stations containing wireless schedulers, supporting task offloading and communication adaptation affected by the service profiles of underlying services.
[0022] Figure 13 It provides an interactive diagram of the interactions between client devices, orchestrators, compute nodes, and base stations including wireless schedulers, and supports performance monitoring and corresponding communication adaptations.
[0023] Figure 14 This is a schematic diagram illustrating the process of establishing a bearer between a client device and a computing node in the network, initiated by a computing node in the network.
[0024] Figure 15 Example service profile and service quality management flowchart. Detailed Implementation
[0025] The detailed description below, taken in conjunction with the accompanying drawings, is intended to describe various configurations and is not intended to represent the only configuration in which the concepts described herein can be practiced. The detailed description includes specific details to provide a thorough understanding of the various concepts. However, those skilled in the art will understand that these concepts can be practiced without these specific details. In some cases, to avoid obscuring these concepts, known structures and components are shown in block diagram form.
[0026] Several aspects of telecommunications systems will now be introduced in conjunction with various apparatuses and methods. These apparatuses and methods will be described in detail below and illustrated with accompanying drawings as various modules, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements can be implemented by electronic hardware, computer software, or any combination thereof. Whether an element is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system.
[0027] For example, a single element, any part of an element, or any combination of elements can be implemented as a “processing system” comprising one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, system-on-a-chip (SoCs), baseband processors, field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform the various functions described in this disclosure. One or more processors in a processing system can execute software. Software should be understood broadly as instructions, instruction sets, code, code segments, program code, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description languages, or other names.
[0028] Therefore, in one or more example aspects, the functionality can be implemented by hardware, software, or any combination thereof. If implemented by software, these functions can be stored or encoded as one or more instructions or code on a computer-readable medium. A computer-readable medium includes a computer storage medium. The storage medium can be any available medium accessible to a computer. By way of example, and not limitation, such a computer-readable medium can include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), optical disc storage, magnetic disk storage, other magnetic storage devices, combinations of computer-readable media of the types described above, or any medium that can be used to store computer-executable code in the form of instructions or data structures and is accessible to a computer.
[0029] Figure 1This is a schematic diagram illustrating a wireless communication system and access network 100. The wireless communication system (also known as a wireless wide area network (WWAN)) includes a base station 102, user equipment (UE) 104, an evolved packet core network (EPC) 160, and another core network 190 (e.g., a 5G core network (5GC)). Base station 102 may include macro cells (high-power cellular base stations) and / or small cells (low-power cellular base stations). Macro cells include base stations. Small cells include home cells, pico cells, and micro cells.
[0030] Base station 102 configured as 4G LTE (collectively referred to as Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN)) can interface with EPC 160 via backhaul link 132 (e.g., SI interface). Base station 102 configured as 5G NR (collectively referred to as Next Generation Radio Access Network (NG-RAN)) can interface with core network 190 via backhaul link 184. Among other functions, base station 102 can perform one or more of the following functions: user data transmission, radio channel encryption and decryption, integrity protection, header compression, mobility control functions (e.g., handover, dual connectivity), inter-cell interference coordination, connection establishment and release, load balancing, non-access stratum (NAS) message distribution, NAS node selection, synchronization, radio access network (RAN) sharing, multimedia broadcast multicast service (MBMS), user and device tracking, RAN information management (RIM), paging, location, and warning message delivery. Base stations 102 can communicate with each other directly or indirectly (e.g., via EPC 160 or core network 190) via backhaul link 134 (e.g., X2 interface). Backhaul link 134 can be wired or wireless.
[0031] Base station 102 can wirelessly communicate with UE 104. Each base station 102 can provide communication coverage for a corresponding geographic coverage area 110. Overlapping geographic coverage areas 110 may exist. For example, small cell 102' may have a coverage area 110' that overlaps with the coverage areas 110 of one or more macro base stations 102. A network containing small cells and macro cells can be referred to as a heterogeneous network. Heterogeneous networks may also include evolved home nodes (eNBs) (HeNBs), which can provide services to a restricted group called a closed subscriber group (CSG). The communication link 120 between base station 102 and UE 104 may include uplink (UL) (also known as reverse link) transmission from UE 104 to base station 102 and / or downlink (DL) (also known as forward link) transmission from base station 102 to UE 104. Communication link 120 may employ multiple-input multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming, and / or transmit diversity. The communication link may be implemented using one or more carriers. Base station 102 / UE 104 can use spectrum with a bandwidth of up to 7 MHz (e.g., 5, 10, 15, 20, 100, 400 MHz, etc.) per carrier for transmission, using a total of Yx MHz (x component carriers) for transmission in carrier aggregation in each direction. Carriers can be adjacent or non-adjacent. Carrier allocation can be asymmetrical in the DL and UL directions (e.g., more or fewer carriers allocated to DL than to UL). Component carriers can include primary component carriers and one or more secondary component carriers. The primary component carrier can be referred to as the primary cell (PCell), and the secondary component carriers can be referred to as secondary cells (SCells).
[0032] Some UEs 104 can communicate with each other via device-to-device (D2D) communication link 158. D2D communication link 158 can use DL / UL WWAN spectrum. D2D communication link 158 can use one or more sidelink channels, such as the Physical Sidelink Broadcast Channel (PSBCH), Physical Sidelink Discovery Channel (PSDCH), Physical Sidelink Shared Channel (PSSCH), and Physical Sidelink Control Channel (PSCCH). D2D communication can be implemented through various wireless D2D communication systems, such as FlashLinQ, WiMedia, Bluetooth, ZigBee, Wi-Fi based on the IEEE 802.11 standard, LTE, or NR.
[0033] The wireless communication system may also include a Wi-Fi access point (AP) 150 that communicates with the Wi-Fi station (STA) 152 via a communication link 154 in the 5 GHz unlicensed spectrum. When communicating in the unlicensed spectrum, the STA 152 / AP 150 may perform a clear channel assessment (CCA) before communication to determine whether the channel is available.
[0034] Cell 102' can operate in licensed and / or unlicensed spectrum. When operating in unlicensed spectrum, cell 102' can adopt New Radio (NR) and use the same 5 GHz unlicensed spectrum as Wi-Fi Access Point (AP) 150. When cell 102' adopts NR in unlicensed spectrum, it can improve the coverage and / or increase the capacity of the access network.
[0035] Base station 102, whether cell 102' or large area (e.g., macro base station), can include evolved Node B (eNB), gNodeB (gNB), or other types of base stations. Some base stations, such as gNB 180, can communicate with user equipment (UE) 104 in conventional sub-6 GHz spectrum, millimeter wave (mmW) frequencies, and / or near-millimeter wave frequencies. When gNB 180 operates at millimeter wave or near-millimeter wave frequencies, gNB 180 can be referred to as a millimeter wave base station. Extremely high frequency (EHF) is a part of the radio frequency (RF) spectrum in the electromagnetic spectrum. The EHF range is from 30 GHz to 300 GHz, with wavelengths between 1 mm and 10 mm. Radio waves in this band can be called millimeter waves. Near-millimeter waves extend down to 3 GHz with wavelengths of 100 mm. The ultra-high frequency (SHF) band is between 3 GHz and 30 GHz, also known as centimeter waves. Communication using millimeter wave / near-millimeter wave RF bands (e.g., 3 GHz - 300 GHz) has extremely high path loss and short range. The millimeter-wave base station 180 can employ beamforming 182 with the UE 104 to compensate for extremely high path loss and short distance.
[0036] Base station 180 can transmit beamforming signals to UE 104 in one or more transmit directions 108a. UE 104 can receive beamforming signals from base station 180 in one or more receive directions 108b. UE 104 can also transmit beamforming signals to base station 180 in one or more transmit directions. Base station 180 can receive beamforming signals from UE 104 in one or more receive directions. Base station 180 / UE 104 can perform beam training to determine their respective optimal receive and transmit directions. The transmit and receive directions of base station 180 can be the same or different. The transmit and receive directions of UE 104 can be the same or different.
[0037] The Evolved Packet Core (EPC) 160 may include a Mobility Management Entity (MME) 162, other MMEs 164, a Serving Gateway 166, a Multimedia Broadcast Multicast Service (MBMS) Gateway 168, a Broadcast Multicast Service Center (BM-SC) 170, and a Packet Data Network (PDN) Gateway 172. MME 162 can communicate with the Home Subscriber Server (HSS) 174. MME 162 is the control node that handles signaling between UE 104 and EPC 160. Typically, MME 162 provides bearer and connection management. All user Internet Protocol (IP) packets are transmitted through the Serving Gateway 166, which is itself connected to the PDN Gateway 172. The PDN Gateway 172 provides UE IP address allocation and other functions. The PDN Gateway 172 and BM-SC 170 are connected to the IP Service 176. The IP Service 176 may include the Internet, intranets, IP Multimedia Subsystem (IMS), Packet Switched (PS) streaming services, and / or other IP services. The BM-SC170 provides MBMS user service configuration and delivery functions. The BM-SC170 can serve as an entry point for content provider MBMS transmissions, authorizing and initiating MBMS bearer services within a Public Land Mobile Network (PLMN), and scheduling MBMS transmissions. The MBMS gateway 168 can distribute MBMS traffic to base station 102 belonging to a Multicast-Broadcast Single Frequency Network (MBSFN) area, broadcast specific services to the area, and is responsible for session management (start / stop) and collecting billing information related to Enhanced MBMS (eMBMS).
[0038] The core network (CN) 190 may include Access and Mobility Management Functions (AMF) 192, other AMFs 193, Location Management Functions (LMF) 198, Session Management Functions (SMF) 194, and User Plane Functions (UPF) 195. AMF 192 can communicate with Unified Data Management (UDM) 196. AMF 192 is the control node that handles signaling between UE 104 and the core network 190. Typically, SMF 194 provides QoS flow and session management. All user Internet Protocol (IP) packets are transmitted through UPF 195. UPF 195 provides UE IP address allocation and other functions. UPF 195 connects to IP Service 197. IP Service 197 may include the Internet, intranet, IP Multimedia Subsystem (IMS), packet-switched (PS) streaming service, and / or other IP services.
[0039] A base station may also be referred to as a gNB, Node B, evolved Node B (eNB), access point, base transceiver station, wireless base station, wireless transceiver, transceiver function, basic service set (BSS), extended service set (ESS), transmit / receive point (TRP), or other appropriate terms. Base station 102 provides UE 104 with access to EPC 160 or core network 190. Examples of UE 104 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, GPS devices, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablets, smart devices, wearable devices, vehicles, electricity meters, gas pumps, large or small kitchen appliances, medical devices, implants, sensors / actuators, displays, or any other similarly functional device. Some UEs 104 may be referred to as Internet of Things (IoT) devices (e.g., parking meters, gas pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as site, mobile station, user station, mobile unit, user unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile user station, access terminal, mobile terminal, radio terminal, remote terminal, handheld device, user agent, mobile client, client or other appropriate terms.
[0040] Although this disclosure may relate to 5G New Radio (NR), it may also be applied to other similar fields, such as LTE, LTE-A, Code Division Multiple Access (CDMA), Global System for Mobile communications (GSM), or other wireless / radio frequency access technologies.
[0041] Figure 2This is a block diagram illustrating communication between base station 210 and user equipment (UE) 250 in the access network. In the downlink (DL), IP packets from the Evolved Packet Core (EPC) 160 can be provided to controller / processor 275. Controller / processor 275 implements Layer 3 and Layer 2 functions. Layer 3 includes the Radio Resource Control (RRC) layer, and Layer 2 includes the Packet Convergence Protocol (PDCP) layer, Radio Link Control (RLC) layer, and Medium Access Control (MAC) layer. The controller / processor 275 provides RRC layer functions related to system information (e.g., Master Information Block (MIB), System Information Blocks (SIBs)) broadcasting, RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), Heterogeneous Radio Access Technology (RAT) mobility, and measurement configuration for UE measurement reporting; it provides PDCP layer functions related to header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; it provides RLC layer functions related to uplink packet data unit (PDU) transmission, error correction via Automatic Repeat Request (ARQ), concatenation, segmentation, and reassembly of RLC service data units (SDUs), resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and it provides functions related to mapping between logical channels and transport channels, multiplexing of MAC SDUs on transport blocks (TBs), and MAC... SDU performs MAC layer functions related to demultiplexing on TB, scheduling information reporting, error correction via Hybrid Automatic Repeat Request (HARQ), priority handling, and logical channel priority.
[0042] Transmit (TX) processor 216 and receive (RX) processor 270 implement Layer 1 functions related to various signal processing functions. Layer 1, including the physical (PHY) layer, may include error detection of the transport channel, forward error correction (FEC) encoding / decoding of the transport channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and multiple-input multiple-output (MIMO) antenna processing. TX processor 216 processes signal constellation mapping according to various modulation schemes (e.g., Binary Phase-Shift Keying (BPSK), Quadrature Phase-Shift Keying (QPSK), M-Phase-Shift Keying (M-PSK), and M-Quadrature Amplitude Modulation (M-QAM)). The encoded and modulated symbols can then be split into parallel streams. Each stream can then be mapped to an orthogonal frequency division multiplexing (OFDM) subcarrier, multiplexed with a reference signal (e.g., a pilot) in the time and / or frequency domains, and then combined by an inverse fast Fourier transform (IFFT) to generate a physical channel carrying a time-domain OFDM symbol stream. The OFDM streams are spatially precoded to generate multiple spatial streams. Channel estimates from channel estimator 274 can be used to determine coding and modulation schemes, as well as spatial processing. The channel estimates can be derived from feedback of the reference signal and / or channel conditions transmitted by UE 250. Each spatial stream can then be provided to a different antenna 220 via an independent transmitter 218TX. Each transmitter 218TX can be transmitted using a radio frequency (RF) carrier modulated with the corresponding spatial stream.
[0043] At UE 250, each receiver 254RX receives signals through its corresponding antenna 252. Each receiver 254RX recovers the information modulated on the RF carrier and provides the information to the receive (RX) processor 256. The TX processor 268 and RX processor 256 implement Layer 1 functions related to various signal processing functions. The RX processor 256 can perform spatial processing on the information to recover any spatial stream directed towards UE 250. If there are multiple spatial streams directed towards UE 250, they can be merged by the RX processor 256 into a single OFDM symbol stream. The RX processor 256 then uses a Fast Fourier Transform (FFT) to convert the OFDM symbol stream from the time domain to the frequency domain. The frequency domain signal includes an independent OFDM symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier, along with the reference signal, are recovered and demodulated by determining the most likely signal constellation point transmitted by base station 210. These soft decisions can be based on a channel estimate calculated by channel estimator 258. The soft decision is then decoded and deinterleaved to recover the data and control signals initially transmitted by base station 210 on the physical channel. The data and control signals are then provided to controller / processor 259, which implements Layer 3 and Layer 2 functions.
[0044] Controller / processor 259 may be associated with memory 260, which stores program code and data. Memory 260 may be referred to as computer-readable medium. In the uplink (UL), controller / processor 259 provides demultiplexing, packet reassembly, decryption, header decompression, and control signal processing between transport and logical channels to recover IP packets from EPC 160. Controller / processor 259 is also responsible for error detection using acknowledgment (ACK) and / or denial (NACK) protocols to support HARQ operation.
[0045] Similar to the downlink transmission functions described in base station 210, controller / processor 259 provides RRC layer functions related to system information (e.g., MIB, SIBs) acquisition, RRC connection, and measurement reporting; provides PDCP layer functions related to header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); provides RLC layer functions related to uplink PDU transmission, error correction via ARQ, concatenation, segmentation, and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and provides MAC layer functions related to mapping between logical channels and transport channels, multiplexing of MAC SDUs on TB, demultiplexing of MAC SDUs from TB, scheduling information reporting, error correction via HARQ, priority processing, and logical channel priority.
[0046] The channel estimate derived by channel estimator 258 based on a reference signal or feedback from base station 210 can be used by TX processor 268 to select appropriate coding and modulation schemes and facilitate spatial processing. The spatial stream generated by TX processor 268 can be provided to different antennas 252 via independent transmitters 254TX. Each transmitter 254TX can be transmitted using the corresponding spatial stream modulated on an RF carrier. The uplink transmission is processed at base station 210 in a manner similar to that described in relation to the receiver function of UE 250. Each receiver 218RX receives signals through its corresponding antenna 220. Each receiver 218RX recovers the information modulated on the RF carrier and provides the information to RX processor 270.
[0047] Controller / processor 275 may be associated with memory 276, which stores program code and data. Memory 276 may be referred to as computer-readable medium. In the uplink, controller / processor 275 provides demultiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transport channel and the logical channel to recover IP packets from user equipment (UE) 250. IP packets from controller / processor 275 may be provided to evolved packet core (EPC) 160. Controller / processor 275 is also responsible for error detection using acknowledgment (ACK) and / or negative acknowledgment (NACK) protocols to support Hybrid Automatic Repeat Request (HARQ) operation.
[0048] New Radio (NR) can refer to a wireless device configured to operate under a new air interface (e.g., a non-Orthogonal Frequency Division Multiple Access (OFDMA) air interface) or a fixed transport layer (e.g., a non-Internet Protocol (IP) layer). NR may employ Orthogonal Frequency Division Multiplexing (OFDM) with a Cyclic Prefix (CP) in both uplink and downlink, and may include support for half-duplex operation using Time Division Duplex (TDD). NR may include enhanced mobile broadband (eMBB) services targeting wide bandwidth (e.g., above 80 MHz), millimeter wave (mmW) services targeting high carrier frequencies (e.g., 60 GHz), massive machine-type communications (mMTC) services targeting non-backward-compatible MTC technologies, and / or mission-critical services targeting ultra-reliable low-latency communications (URLLC) services.
[0049] It supports a single component carrier bandwidth of 100 MHz. In one example, an NR resource block (RB) can span 12 subcarriers with a subcarrier bandwidth of 60 kHz and a duration of 0.25 ms, or a bandwidth of 30 kHz and a duration of 0.5 ms (similarly, a 15 kHz subcarrier spacing (SCS) has a bandwidth of 50 MHz over a duration of 1 ms). Each radio frame can consist of 10 subframes (10, 20, 40, or 80 NR slots) with a length of 10 ms. Each slot can indicate the link direction used for data transmission (i.e., downlink (DL) or uplink (UL)), and the link direction of each slot can be dynamically switched. Each slot can include DL / UL data and DL / UL control data. The UL and DL slots of NR can be combined as follows. Figure 5 and Figure 6 More detailed description.
[0050] The NR Radio Access Network (RAN) may include a Central Unit (CU) and a Distributed Unit (DU). An NR Base Station (BS) (e.g., gNB, 5G Node B, Node B, Transceiver Point (TRP), Access Point (AP)) may correspond to one or more BSs. NR cells may be configured as Access Cells (ACells) or Data-Only Cells (DCells). These cells may be configured by the RAN (e.g., a Central Unit or a Distributed Unit). DCells may be used for carrier aggregation or dual connectivity and may not be used for initial access, cell selection / reselection, or handover. In some cases, DCells may not transmit synchronization signals (SS), and in others, they may transmit SS. NR base stations may transmit downlink signals to the UE to indicate the cell type. Based on the cell type indication, the UE may communicate with the NR base station. For example, the UE may determine the NR base station for cell selection, access, handover, and / or measurement based on the indicated cell type.
[0051] Figure 3 The logical architecture of a distributed radio access network (RAN) 300 is illustrated exemplarily according to aspects of this disclosure. A 5G access node 306 may include an access node controller (ANC) 302. The ANC may be the central unit (CU) of the distributed RAN. A backhaul interface to a next-generation core network (NG-CN) 304 may terminate at the ANC. A backhaul interface to a neighboring next-generation access node (NG-AN) 310 may terminate at the ANC. The ANC may include one or more transceiver points (TRPs) 308 (also referred to as BS, NR BS, Node B, 5G NB, AP, or other terms). As mentioned above, TRP can be used interchangeably with "cell".
[0052] TRP 308 may be a distributed unit (DU). A TRP may connect to one ANC (ANC 302) or multiple ANCs (not shown). For example, for RAN sharing, Radio-as-a-Service (RaaS), and service-specific ANC deployments, a TRP may connect to multiple ANCs. A TRP may include one or more antenna ports. A TRP may be configured to provide traffic services to the UE individually (e.g., dynamically selected) or jointly (e.g., jointly transmitted).
[0053] The local architecture of the distributed RAN 300 can be used to illustrate the fronthaul definition. The architecture can define fronthaul solutions that support different deployment types. For example, the architecture can be based on transport network capabilities (e.g., bandwidth, latency, and / or jitter). The architecture can share features and / or components with LTE. Depending on some aspects, the Next Generation Access Node (NG-AN) 310 can support dual connectivity with NR. The NG-AN can share a common fronthaul for LTE and NR.
[0054] The architecture enables collaboration between and within TRPs 308. For example, collaboration can be pre-defined within a TRP and / or implemented across TRPs via ANC 302. Depending on certain aspects, inter-TRP interfaces may not be required or may not exist.
[0055] Depending on certain aspects, the architecture of the distributed RAN 300 can be dynamically configured with logical function splitting. Packet Data Convergence Protocol (PDCP), Radio Link Control (RLC), and Media Access Control (MAC) protocols can be adaptively placed in the ANC or TRP.
[0056] Figure 4 The physical architecture of the distributed RAN 400 is illustrated exemplarily according to aspects of this disclosure. A centralized core network unit (C-CU) 402 can host core network functions. The C-CU can be centrally deployed. C-CU functions can be offloaded (e.g., to Advanced Wireless Services (AWS)) to handle peak capacity. A centralized RAN unit (C-RU) 404 can host one or more ANC functions. Optionally, the C-RU can locally host core network functions. The C-RU can be distributed. The C-RU can be closer to the network edge. A distributed unit (DU) 406 can host one or more TRPs. The DU can be located at the network edge and has radio frequency (RF) functions.
[0057] Figure 5 This is a schematic diagram 500 illustrating an example of a DL center timeslot. The DL center timeslot may include a control section 502. The control section 502 may exist in the initial or beginning portion of the DL center timeslot. The control section 502 may include various scheduling and / or control information corresponding to the various portions of the DL center timeslot. In some configurations, the control section 502 may be a physical DL control channel (PDCCH), such as... Figure 5 As shown. The DL center time slot may also include a DL data portion 504. The DL data portion 504 may sometimes be referred to as the payload of the DL center time slot. The DL data portion 504 may include communication resources used for transmitting DL data from a scheduling entity (e.g., a user equipment (UE) or a base station (BS)) to a subordinate entity (e.g., a UE). In some configurations, the DL data portion 504 may be a physical DL shared channel (PDSCH).
[0058] The DL center time slot may also include a common UL section 506. The common UL section 506 may sometimes be referred to as a UL burst, a common UL burst, and / or other various applicable terms. The common UL section 506 may include feedback information corresponding to other sections of the DL center time slot. For example, the common UL section 506 may include feedback information corresponding to the control section 502. Non-limiting examples of feedback information may include ACK signals, NACK signals, HARQ indicators, and / or other various applicable types of information. The common UL section 506 may include additional or alternative information, such as information related to the Random Access Channel (RACH) procedure, scheduling requests (SR), and other various applicable types of information.
[0059] like Figure 5 As shown, the end of the DL data section 504 and the start of the common UL section 506 can be separated in time. This time separation may sometimes be referred to as a gap, guard period, guard interval, and / or other various applicable terms. This separation provides time for the switch from DL communication (e.g., a receiving operation of a subordinate entity (e.g., a UE)) to UL communication (e.g., a transmitting operation of a subordinate entity (e.g., a UE)). Those skilled in the art will understand that the above is merely one example of a DL central timeslot, and alternative structures with similar characteristics may exist without departing from the aspects described herein.
[0060] Figure 6 This is a schematic diagram 600 illustrating an example of a UL center time slot. The UL center time slot may include a control section 602. The control section 602 may be present at the beginning or start of the UL center time slot. Figure 6 The control section 602 can be combined with the above. Figure 5 The control portion 502 is described similarly. The UL center timeslot may also include a UL data portion 604. The UL data portion 604 may sometimes be referred to as the payload of the UL center timeslot. The UL portion may refer to the communication resources used for transmitting UL data from a subordinate entity (e.g., the UE) to a scheduling entity (e.g., the UE or the BS). In some configurations, the control portion 602 may be a physical DL control channel (PDCCH).
[0061] like Figure 6As shown, the end of control section 602 and the start of UL data section 604 can be separated in time. This time separation may sometimes be referred to as a gap, protection period, protection interval, and / or other various applicable terms. This separation provides time for switching from DL communication (e.g., a receiving operation of a scheduling entity) to UL communication (e.g., a transmitting operation of a scheduling entity). The UL central time slot may also include the common UL section 606. Figure 6 The public UL section 606 in the document can be combined with the above. Figure 5 The description of common UL section 506 is similar. Common UL section 606 may also include or instead contain information such as channel quality indicators (CQI), measurement reference signals (SRS), and various other applicable types. Those skilled in the art will understand that the above is merely one example of a UL center slot, and alternative structures with similar characteristics may exist without departing from the aspects described herein.
[0062] In some cases, two or more dependent entities (e.g., UEs) can communicate with each other using sidechain signals. Practical applications of such sidechain communication can include public safety, proximity services, UE-to-network relay, vehicle-to-vehicle (V2V) communication, Internet of Things (IoE) communication, Internet of Things (IoT) communication, mission-critical mesh networks, and / or various other applicable applications. Generally, a sidechain signal can refer to a signal transmitted from one dependent entity (e.g., UE1) to another dependent entity (e.g., UE2) without relaying communication through a scheduling entity (e.g., UE or BS), although the scheduling entity may be used for scheduling and / or control purposes. In some examples, sidechain signals can communicate using licensed spectrum (unlike wireless LANs that typically use unlicensed spectrum).
[0063] In wireless communication systems that support the offloading of computationally intensive tasks, client devices—such as smartphones, smart glasses, extended reality (XR) headsets, and Internet of Things (IoT) devices—can host applications with significant computational demands. These demands can be quantified using various metrics, including CPU cycles and memory usage. Client devices, also known as tenant devices, application hosts, or similar devices, may encounter situations where the computational resources required by an application exceed what the client device can (or tends to) provide. For example, an application may require intensive CPU operations that the client device's CPU cannot complete in a timely manner; the client device may be limited by battery life and tend to offload computational tasks to devices with more power resources; and / or the application may require more memory than the client device can allocate.
[0064] An example system supporting compute offloading may include client devices, one or more compute nodes capable of performing compute tasks on behalf of the client devices, and an orchestrator node responsible for managing the allocation of compute tasks to the compute nodes in a manner that meets the performance requirements of the underlying services. A set of nodes participating in a specific task, or a set of nodes managed by a specific orchestrator, may be referred to within a communication system as a “cluster,” “compute cluster,” or “subnetwork.” Compute nodes may also be referred to as worker nodes, compute servers, leased equipment, etc. An orchestrator may be referred to as a master node, a combined management function, a compute management function, a cluster manager, or similar terms. Compute nodes and orchestrators may include mobile devices, user equipment (UEs), nodes within a wireless network, or similar entities. For ease of discussion, it is assumed that the client devices are mobile devices and / or user equipment (UEs), although the concepts disclosed herein also apply to clients located within a wireless network (e.g., a base station in a wireless network may invoke one or more compute nodes to assist in compute-intensive assessments of mobility standards for the devices it serves). It is important to note that the term “mobile device” broadly refers to a device serving within a wireless network and does not necessarily mean that the device is physically mobile. For example, a mobile device can be a Customer Premises Equipment (CPE) node, which is located in a fixed position but appears as a device in the network service to the wireless network.
[0065] In many cases, compute-intensive services impose specific performance requirements. For example, rendering applications may need to support display operations at a specific frame rate, ensuring that completed frames are delivered in time for the next scheduled display update. Typically, such performance requirements may include a maximum allowable computation time—that is, the results of the computation task must be available to client applications before the deadline. Furthermore, some tasks may have additional requirements, such as target accuracy or convergence of the results. There may also be requirements related to the data flow supporting the computation task, such as expected (maximum and / or average) group size, expected (precise, minimum, maximum and / or approximate) periodicity, etc. In a compute cluster executing one or more tasks, the orchestrator must understand both the performance requirements of the tasks and the available compute resources on the compute nodes within the cluster. This understanding enables the orchestrator to allocate tasks to appropriate compute nodes and ensure that performance requirements are met.
[0066] However, computational requirements are not the only performance constraints affecting computational task operations in distributed systems such as computing clusters. The communication path between client devices and compute nodes, which may be used to transmit task images, data supporting computational operations, and / or the results of those operations, imposes specific constraints on communication traversing that path. For example, a communication path may have associated minimum (or typical) transmission latency, maximum (peak or average) data bandwidth, etc. Therefore, the management of computational tasks must consider not only computational performance requirements but also the impact of the communication paths used to support computational offloading operations. Furthermore, communication systems can adapt to the service requirements of offloading computational tasks, for example, by scheduling wireless resources to optimize the data communication performance of the service (potentially at the expense of other lower-priority, less latency-sensitive data). Such interaction schemes between computational services and the supporting wireless layer can be referred to as integrated communication and computing (ICC), joint communication and computing (JCC), or similar terms.
[0067] This disclosure relates to a method for implementing ICC functionality by managing multiple Quality of Service (QoS) standards between an orchestrator and one or more radio resource schedulers. The method enables the scheduler to deliver computational data and results in a timely manner, while allowing the orchestrator to accurately model the expected performance of the communication system. The management of QoS standards can be guided, in whole or in part, by service profiles of one or more corresponding underlying application computational tasks. It is important to note that the use of "QoS" here differs from the concept of communication QoS; the QoS metrics discussed in this disclosure refer to the performance of the entire service, including both communication and / or computational components. Therefore, the QoS of a computational service may include, overlap with, but is not limited to, the communication QoS of the underlying radio transport layer. For example, in this disclosure, when "QoS" is used to refer to communication performance, it will be explicitly distinguished as "communication QoS".
[0068] The method aims to support communication scheduling consistent with service performance requirements. In one aspect, the method can assist a scheduler for computing services. In a communication system comprising multiple computing nodes distributed across at least one network domain, where the network domain may be a combination of user equipment and / or network equipment, a first node may receive a service profile of the computing service from a second node among the multiple computing nodes. The first node then sends first information derived from the service profile to a third node. The third node may perform scheduling for at least one node in the communication system.
[0069] In another aspect, the method may request and configure a bearer for the computing service based on requirements specified in the service profile. The method may trigger bearer configuration for the computing service. In this case, the first node may receive the service profile for the computing service from the second node. The first node then sends a request to the third node to establish a communication bearer between the third node and the fourth node. The request may include information derived from the service profile.
[0070] In this disclosure, the term "network domain" refers to a logical or functional partition in a communication system, such as a Radio Access Network (RAN) domain and a Core Network (CN) domain. For example, the RAN domain may include base station 102, and the CN domain may include Access and Mobility Management Function (AMF) 192 and / or Session Management Function (SMF) 194. Accordingly, network domain-specific operations may include performing scheduling within the RAN domain or configuring bearers within the CN domain.
[0071] In distributed communication systems, to meet performance requirements, specific services can be efficiently provided through appropriate resource allocation (such as compute offloading). Specifically, the service involves computationally intensive tasks. In this scenario, tasks that are part of the service or application hosted by the client device can be partially offloaded to the compute nodes. The compute nodes are managed by a third entity (called the orchestrator). The architecture establishes a triangular relationship between the client device, compute nodes, and the orchestrator, facilitating the efficient coordination and management of computing resources.
[0072] Figure 7 Figure 700 illustrates the interaction between nodes in a system supporting compute offloading. It shows the interaction between client device 702, compute node 704, and orchestrator 706, which can be collectively considered as a compute cluster. In some embodiments, the cluster may include multiple compute nodes. However, in this case, each compute node is expected to operate substantially independently of the others. Client device 702 communicates with orchestrator 706 to facilitate discovery within the cluster (e.g., client device 702 discovers compute nodes) and offloading management (e.g., assigning specific compute tasks to appropriate compute nodes). Orchestrator 706 communicates with compute node 704 to support compute resource management (e.g., compute node 704 registers with orchestrator 706 and / or determines the level of compute resources available to compute node 704 in a given cluster). Client device 702 communicates with compute node 704 to perform task offloading and deliver task results.
[0073] Figure 7The communication links shown can employ various transmission methods, used individually or in combination, such as the air interface of a wireless communication system (using a protocol stack based on the user plane, control plane, management plane, and / or computation plane), the network interface within a wireless communication system, and the inter-system interface for interaction between one communication system and another. Interactions can be modeled as protocol transactions, application programming interface (API) calls, service-based interface (SBI) calls, data flows, etc., encompassing combinations of different models.
[0074] For example, client device 702 can interact with orchestrator 706 in a wireless network, using a combination of control plane transmission over the air interface and network interface within the network. Simultaneously, it can interact with compute node 704 in the wireless network, using a combination of user plane transmission over the air interface and network interface within the network. Meanwhile, orchestrator 706 interacts with compute node 704 through the network interface. Another example is that client device 702 can interact with orchestrator 706 at a first peer via a device-to-device (D2D) architecture control plane, and at a second peer via a D2D architecture user plane, while orchestrator 706 interacts with compute node 704 via a D2D architecture control plane.
[0075] It should also be understood that Figure 7 Any role shown can co-locate on a single node. For example, client device 702 could host its own orchestrator, or orchestrator 706 could have its own computing resources running as a compute node. In this case, Figure 7 Interactions between co-located roles can be handled as implementation matters within the relevant nodes. For example, if client device 702 and orchestrator 706 co-located on the same device, the offloading management process can be implemented through inter-process communication within the device, APIs between different processes on the device, or similar mechanisms. Throughout this description, for clarity, these functions will be treated as being implemented in different nodes.
[0076] like Figure 7As shown, computation offloading operates based on a triangular architecture. In this architecture, orchestrator 706 manages the allocation and control of computing resources and coordinates with client device 702. Client device 702 offloads computing tasks to compute node 704 and receives results through a configured bearer. This triangular architecture is similar to the Multi-Access Edge Computing (MEC) framework in 5G systems. However, unlike 5G MEC, where compute nodes and orchestrators typically reside in the data network above the core network, the nodes involved in this disclosure can be flexibly located in any part of the network, such as user equipment (UE), radio access network (RAN), core network (CN), and data network (DN). For example, the orchestrator can be located on an element within a UE, base station, or CN. Similarly, compute nodes can be located in different locations, including UEs, base stations, or core network elements.
[0077] This disclosure relates to the characterization of services (such as computing services) through "service profiles," which define the performance requirements of the computing service. The service profiles are exposed to the RAN and / or CN to enable dynamic configuration of network resources.
[0078] The orchestrator 706 can be configured to remain aware of the computing service requirements specified in the service profile and dynamically configure network nodes (e.g., RAN, CN) to meet the computing service requirements. The orchestrator 706 can also coordinate with the RAN to optimize radio resource scheduling based on computing service requirements, or coordinate with the CN to establish and configure bearers between client device 702 and computing node 704 to ensure efficient transmission of data offloaded from computing.
[0079] In this architecture, the position of the CN relative to the orchestrator depends on the node topology for a specific service. In some implementations, the orchestrator may reside within the CN. In other implementations, all nodes may be devices, while the CN is set up separately.
[0080] Although Figure 7 The description in this paper primarily focuses on a single client device, a single orchestrator, and a single compute node, but the architecture is scalable and can be extended to scenarios involving multiple nodes, such as multiple compute nodes. In this context, the orchestrator, compute node, and client device can be referred to as nodes, such as orchestrator node, compute node, and client node. The communication and coordination mechanisms described in this paper are adaptable to multiple compute nodes. These compute nodes can run in parallel to improve system performance.
[0081] The client device 702 can be a UE (User Equipment). However, the concept is not limited to UE and can also be applied to network clients. For example, a compute-assisted framework can be used for network management tasks or other similar applications.
[0082] Figure 8 Figure 800 illustrates a system supporting compute offloading and includes multiple compute nodes located at different locations within the system. It shows an example of a compute cluster serving a first (client) device 802. In addition to the first device 802 itself, the cluster includes a second (orchestrator) device 804, a third device hosting the first compute node (compute node A) 806A, and a cellular network base station (BS) hosting the second compute node (compute node B) 806B. (Whether a client device is considered part of the cluster may vary depending on the implementation; in different implementations, the cluster may be modeled as containing only compute nodes, compute nodes and orchestrators, or all the nodes shown.)
[0083] It is important to note that the "management" of a function can be implemented in various ways depending on the architecture of a specific system. For example, a network-managed compute node (compute node B 806B) can be an edge computing server (MECserver) associated with a base station (BS), while a device-managed compute node (compute node A 806A) can be a system function of a cellular system, and so on. For ease of discussion, the distinction between functions (such as orchestrators, client communication proxies, or compute nodes) and nodes hosting functions is generally not made. That is, communication between a communication proxy on a client device and a compute node function associated with a network node can, for simplicity, be described as communication between a client device and a network node, and so on. However, it should be understood that all participants in a compute cluster use the communication mechanisms of the upper-layer communication system, including various types of interfaces and communication models between nodes.
[0084] exist Figure 8 In this context, the orchestrator 804 can be viewed as the "controller" or "manager" of the cluster, coordinating the computing resources provided by compute nodes A and B (806A-B) and making them available to client devices 802.
[0085] Figure 9 This is flowchart 900, showing an example of offloading computation tasks to a compute node. It demonstrates... Figure 8 A similar system. The nodes involved are... Figure 8 Similarities: Client device 902, orchestrator 904, and two compute nodes (compute node A906A and compute node B906B).
[0086] In step S901, the nodes perform a discovery and cluster formation process. This process may include, for example, the distribution of device capabilities, the registration of client devices 902 and / or compute nodes 906A-B to the orchestrator 904, and negotiation between the orchestrator 904 and the compute nodes 906A-B regarding how many compute resources each node will allocate to the cluster, as well as other activities.
[0087] In step S902, the node performs the task association with the compute node and the distribution of the task image. This step can be implemented using various schemes. The task image can be pre-stored by the orchestrator 904 and distributed to other nodes, or it can be directly provided by the client device 902, or stored in the repository 908 and distributed to compute nodes 906A-B by the orchestrator 904 or the client device 902, and so on.
[0088] In step S903, the client device 902 transmits the data for Task 1 (e.g., a set of input parameters for computation) to the computing node A 906A.
[0089] In step S904, compute node A 906A uses the data transmitted in step S903 as input to execute the mirroring of Task 1.
[0090] In step S905, computing node A 906A returns the result of Task 1 to client device 902. Steps S903-905 can be repeated as needed by the application that generated Task 1. For example, an extended reality (XR) application can periodically stream the input data of each video frame to the computing node (step S903) and receive rendered frames in a timely manner to display to the user (step S905).
[0091] In step S906, the client device 902 transmits the data for Task 2 to the computing node B 906B.
[0092] In step S907, compute node B 906B uses the data transmitted in step S906 as input to execute the mirroring of Task 2.
[0093] In step S908, computing node B 906B returns the result of Task 2 to client device 902. Steps S906-908 can be repeated as needed by the application that generated Task 2. For example, a generative artificial intelligence (AI) application may send a prompt to the computing engine when the user provides a prompt (step S906) and receive the generated response when the task execution ends (step S908).
[0094] In step S909, the node performs performance monitoring. The monitoring may take into account various factors, such as the quality of service (QoS) provided by the communication in the preceding steps, the computing performance of computing nodes A and B (906A-B), the application's requirements for computing tasks, and the quality of experience (QoE) obtained by the client device 902, etc.
[0095] Figure 10 Figure 1000 shows the task offloading and performance monitoring interaction between client device 1002, orchestrator 1004 and compute node 1006. Figure 10The process shown begins after the nodes have discovered each other and formed a cluster, at which point client device 1002 is starting applications that benefit from the computing services.
[0096] In step S1001, client device 1002 sends a service profile to orchestrator 1004. The service profile describes the expected performance requirements and characteristics of the computational tasks required by the application. The service profile may include, for example, latency limits for task completion time, memory requirements, metrics of expected CPU load, expected convergence level, etc. In some embodiments, the service profile may be provided to orchestrator 1004 from a source other than client device 1002, such as a task repository 1008. Specifically, if the service requires "user-space" tasks whose behavior is defined by code provided by client device 1002, the service profile is typically sent by client device 1002. If the service requires "carrier-space" tasks whose execution code is a predefined service provided by a communication system operator, orchestrator 1004 may retrieve the service profile from a task repository maintained by the operator. Other approaches may also be used, such as orchestrator 1004 retrieving the service profile from a third-party external repository 1010. In some embodiments, a single service may contain multiple computing tasks, which may be provided from a single source or different sources and may be assigned to one or more computing nodes.
[0097] In step S1002, the orchestrator 1004 sends a task assignment to the computing node 1006, reserving some computing resources on the computing node 1006 for service. In some embodiments, step S1002 (or the subsequent step S1003) may be followed by an acknowledgment or confirmation message (not shown in the figure) indicating that the assigned computing module has been successfully instantiated on the computing node.
[0098] In step S1003, compute node 1006 obtains the executable image of the task. This step can be performed in various ways. For example, compute node 1006 may receive the task image or repository location from orchestrator 1004 along with the task assignment, or compute node 1006 may retrieve the task image from a repository (e.g., a location provided to compute node 1004 by orchestrator 1004), and so on.
[0099] In step S1004, orchestrator 1004 sends an offload instruction to client device 1002. These instructions provide necessary guidance for client device 1002 to transfer computing task data to the appropriate computing node 1006. The offload instruction may include, for example, the identity of the computing node 1006, parameters used to generate and / or transmit computing task data, etc. In some embodiments, step S1004 may be replaced by an interaction with another node in the communication system responsible for configuring the bearer to client device 1002, as will be discussed further below.
[0100] In step S1005, the client device 1002 uses the information provided in step S1004 to send a set of task data to the computing node 1006. The data can be transmitted as a single message or packet, a data stream, or other incremental form, enabling the computing node 1006 to execute the task image with well-defined input.
[0101] In step S1006, after executing the computing task, computing node 1006 sends the result of the computing task to client device 1002. Steps S1005 and S1006 can occur through various transmission mechanisms, such as one or more data bearers, one or more signaling messages, one or more API calls, etc. These steps can be repeated as required by the service.
[0102] In step S1007, the compute node 1006 sends first performance data to the orchestrator 1004. This data may include, for example, the time required to execute the task, CPU load metrics generated by the compute node 1006 during task execution, and memory consumption indicators for the task.
[0103] In step S1008, the client device 1002 sends second performance data to the orchestrator 1004. The data may include, for example, the elapsed time between task data transmission (starting in step S1005) and result reception (completed in step S1006), an indication of whether the data transmission deadline has been met, and an assessment of result quality (e.g., in the case of a task attempting to approximate a known target where the accuracy of the result is measurable). The second performance data can be considered a service-level QoS or QoE information, indicating the degree to which the overall service performance meets requirements.
[0104] In step S1009, the orchestrator 1004 evaluates the first performance data and / or the second performance data and performs a performance assessment. The assessment may include, for example, comparing the first and / or second performance data with the service profile to determine whether the service's performance expectations are met.
[0105] Figure 11 Flowchart 1100 illustrates an example of a bearer setup between client device 1102 and compute node 1106 in a network initiated by orchestrator 1104. Orchestrator 1104 is configured to be aware of service profiles at the start of the process. For example, service profiles may be obtained in one of the following ways: (1) by negotiating with the client device, (2) by receiving from the compute node, or (3) by retrieving from an external repository containing task images that the operator is willing to support with compute resources.
[0106] As described above, in some embodiments, task assignment to a specific computing node can be indicated to the client device 1102 through an indirect mechanism (such as user plane bearer assignment). Figure 11This demonstrates an example of a message flow where the orchestrator 1104 triggers such bearer assignments through interaction with other nodes in the system, such as the CN node. It is worth noting that... Figure 11 The terminology used is from 5G system design, but it should be understood that some nodes can be replaced by newer 6G nodes with similar functionality.
[0107] like Figure 11 The process shown begins at step S1100, where orchestrator 1104 selects a compute node (e.g., compute node 1106 hosted in the network infrastructure) to handle a specific compute task from client device 1102. The criteria for selecting compute node 1106 may depend on the orchestrator's implementation or the service profile associated with the corresponding application, considering factors such as the task's CPU and memory requirements, the required latency relative to the performance and location of compute node 1106, etc. The process also includes notifying compute node 1106 that it has been selected and transmitting the task image to compute node 1106. Figure 11 As shown in the diagram; these aspects can be carried out in accordance with the other contents described above in this specification.
[0108] In step S1101, orchestrator 1104 sends a session and / or bearer request to the Session Management Function (SMF) so that client device 1102 can exchange computing data with compute node 1106. In some embodiments, the request may initially be sent to a management network function, such as a Policy Control Function (PCF), which may then submit a session establishment request to the SMF. The request sent by orchestrator 1104 may include information such as the identities of client device 1102 and compute node 1106, and the parameters required for the bearer.
[0109] In step S1102, the SMF selects an appropriate communication anchor point, such as a User Plane Function (UPF), to handle the bearer. For example, a particular UPF may be deployed closely with compute node 1106, enabling communication via the UPF to reach compute node 1106 with low latency.
[0110] In step S1103, the SMF requests the UPF to create or modify a Protocol Data Unit (PDU) session to transmit computational data. (If a PDU session with appropriate endpoints already exists between the client device 1102 and the UPF, the PDU session can be modified to add a new bearer. Otherwise, a new PDU session can be created at this stage.)
[0111] In step S1104, the SMF notifies the Access and Mobility Management Function (AMF) PDU of a session update.
[0112] In step S1105, the AMF requests the base station (BS) 1108 to send a reconfiguration to the client device 1102 to configure an appropriate radio bearer (e.g., user plane data radio bearer or computing radio bearer) to carry computing data.
[0113] In step S1106, BS1108 sends a configuration message, such as a reconfiguration message for the Radio Resource Control (RRC) protocol, to client device 1102. Client device 1102 responds in a manner indicating that the requested configuration has been applied.
[0114] In step S1107, the client device 1102 uses the newly configured bearer to transmit the data of the computing task to the UPF, and the UPF further routes the data to the computing node 1106.
[0115] In step S1108, the UPF routes the computation data to compute node 1106. Compute node 1106 uses the transmitted data to perform a task (not shown as a separate step in the diagram) to generate the computation task results.
[0116] In step S1109, the computing node 1106 transmits the computing task results to the UPF for further routing to the client device 1102.
[0117] In step S1110, the UPF uses the newly configured bearer to transmit the computation task results to the client device 1102.
[0118] By SMF Figure 11 The interactions triggered in this process are similar to the mechanisms used in MEC operations in 5G systems. The difference lies in the fact that the orchestrator 1104 directly participates in step S1101 to trigger the configuration process. This participation can be beneficial in clusters with dynamically changing membership, where compute nodes frequently leave or join the cluster. The orchestrator 1104's real-time or near-real-time involvement in managing task allocation to compute nodes helps to efficiently utilize such dynamic computing resources.
[0119] In some embodiments, a compute node (which may be one of multiple compute nodes participating in a particular application) may be aware of the service profile and / or the performance requirements of the compute task (e.g., if compute node 1106 hosts a set of static or semi-static microservices). In this case, compute node 1106 may initiate a session or host request itself, rather than orchestrator 1104 (similar to...). Figure 11 (Step S1101 in the above). In this mode, each of one or more compute nodes can trigger the establishment of a communication session (e.g., a PDU session with a user plane bearer, a compute session with a compute plane bearer, etc.) between the client device 1102 and the compute node 1106 itself. Information about the resulting session and / or bearer may then need to be passed to the orchestrator 1104 (e.g., by the compute node 1106 or the client device 1102) so that the orchestrator 1104 can monitor the performance of the service.
[0120] Figure 12 This is a diagram 1200 showing an example of interaction between client device 1202, orchestrator 1204, compute node 1206 and base station (BS) 1208 containing a wireless scheduler, supporting task offloading and communication adaptation affected by the service profiles of the underlying services.
[0121] Figure 12 This demonstrates a typical set of interactions between nodes that facilitates service-aware scheduling, i.e., allocating wireless resources in a manner sensitive to compute service requirements. This set of interactions can be seen as an enabler for ICC functionality, as it allows the wireless system's communication mechanisms to adapt to providing compute services. Compute node 1206 can be a group of compute nodes. For example, as... Figure 12 As shown, it may include two compute nodes: a first compute node 1206-1 located in the network and a second compute node 1206-2 located on a mobile device. It should be noted that including two compute nodes is merely an example. Some embodiments may have only one compute node, whether on a network node or a mobile device, while other embodiments may include multiple compute nodes in a cluster managed by orchestrator 1204. The functionality of these nodes is consistent with the foregoing description.
[0122] Similarly, BS 1208 can be a group of base stations (BSs). For example, Figure 12 Two Base Stations (BSs) 1208-1 and 1208-2 are shown, serving client device 1202 and the second computing node 1206-2, respectively. Each BS contains a wireless scheduler. In some embodiments, a single BS can serve all relevant mobile devices. The scheduler in each BS is responsible for allocating wireless resources for wireless communication over the air interface and scheduling transmissions and receptions with mobile devices to utilize the allocated wireless resources. Figure 12In this example, the functionality is indicated by arrows labeled "Scheduling" from BS 1208 to client device 1202 and second compute node 1206-2, suggesting that in this example, both client device 1202 and second compute node 1206-2 are considered mobile devices whose communication is scheduled by BS 1208. In this example, orchestrator 1204 is not depicted as being scheduled by any BS—for example, orchestrator 1204 could be deployed in a network node—but it should be understood that embodiments where orchestrator 1204 is also located on a mobile device and its communication is scheduled by a BS are equally valid. In this case, orchestrator 1204 could be served by the same BS as the client device, the same BS as the compute node, or a separate BS.
[0123] In step S1201, client device 1202 transmits a service profile to orchestrator 1204. This step represents one of several alternative methods for orchestrator 1204 to obtain the service profile. In other embodiments, step S1201 may involve transferring the service profile from a repository to orchestrator 1204, or the service profile being pre-configured within orchestrator 1204 itself. The key function of this step is to ensure that orchestrator 1204 possesses the service profile for subsequent operations.
[0124] In step S1202, the orchestrator 1204 performs service-related computing tasks and assigns them to each computing node.
[0125] In step S1203, orchestrator 1204 passes information derived from the service profile and / or the service profile itself to each BS 1208. In some embodiments, the information may include one or more traffic patterns associated with the service (or a specific task derived from the service), such as maximum packet size, peak or average data rate, latency requirements, expected transmission periodicity, etc. In this case, the service or task may be associated, for example, with a first traffic pattern for transmitting computation task input data from client device 1202 (and / or to compute node 1206), and a second traffic pattern for transmitting computation task results to client device 1202 (and / or from compute node 1206). For example, the rendering task of an XR service may be associated with a first traffic pattern for transmitting input data to the rendering engine, and a second traffic pattern for transmitting rendered frames to client device 1202. The first traffic pattern may have associated periodicity (e.g., determined by the frame rate or tick rate of the underlying application) and an average data rate (e.g., determined by the expected size of the input data required to render one frame, such as control input, pose data, etc.). The second traffic pattern may have associated periodicity (e.g., determined by the frame rate), latency requirements (e.g., determined by the deadline for delivering frames to the user's display), and peak or average data rate and / or packet size (e.g., determined by the size of the rendered frames). Traffic patterns and other information related to the service or task may be explicitly described as part of the service profile, or derived by the orchestrator 1204 or BS 1208 from information in the service profile.
[0126] In step S1203, orchestrator 1204 may also send one or more link utilization requests, such as traffic patterns between client device 1202 and compute node 1206 derived from a service profile. This information can be used by base station (BS) 1208 in its scheduling algorithm for uplink and downlink radio resource allocation. For example, if the service is associated with a periodic traffic pattern and maximum packet size, BS 1208 may allocate radio resource grants in a manner that matches the periodicity and size of the traffic pattern. In some embodiments, these grants may be dedicated to a specific service, task, and / or bearer, while in other embodiments, grants may be self-filled by the device based on certain criteria (e.g., a priority scheme, where some or all of the device's data to be transmitted bearers are considered). In some embodiments, the scheduling algorithm of BS 1208 may be determined by the BS implementation, and the supporting information in step S1203 may be configured according to a standardized mechanism.
[0127] In step S1204, orchestrator 1204 delivers a compute node assignment to client device 1202, such as an instruction to offload a specific task to a specific compute node. The assignment may, for example, identify the communication bearer that client device 1202 will use to offload compute activity to compute node 1206. Figure 12 In the example, with two compute nodes 1206-1 and 1206-2, step S1204 may include two assignments (one for each compute node), or step S1204 may be executed twice (once for each compute node). Preferably, step S1204 is performed after step S1203 to ensure that BS 1208 is aware of the service scheduling requirements before client device 1202 initiates communication with compute node 1206. However, step S1204 may also be performed before step S1203, allowing scheduling to proceed in a best-effort manner before BS 1208 learns the service profile or information derived from it.
[0128] In step S1205, the client device 1202 and the computing node 1206 communicate with each other via... Figure 12 The bidirectional process marked "Offload" exchanges computational data and results. The communication in step S1205... Figure 12 The arrows represent direct routes, but in the context of a wireless system, actual data transmission may traverse one or more BSs, one or more additional network nodes (such as core network (CN) nodes), etc., forming an intra-system route between client device 1202 and computing node 1206. It should be understood that... Figure 12 The topology shown is for illustrative purposes only. Actual systems may involve different interactions between a particular node and one or more BSs, depending on which functions are implemented in the mobile device and which are implemented in the network node.
[0129] In some embodiments, step S1203 may be performed by client device 1202 instead of orchestrator 1204. That is, client device 1202 may deliver a service profile or information derived from a service profile to BS 1208. Communication between client device 1202 and BS 1208 for delivering information may, for example, involve Radio Resource Control (RRC) protocol messages, such as UEAssistanceInformation messages, in which client device 1202 indicates information to assist the scheduler (e.g., traffic patterns, latency requirements, packet sizes, etc., as described in the aforementioned information background for orchestrator 1204). However, it should be noted that in this case, communication between different BSs may be required. For example, if client device 1202 is served by first BS 1208-1, while compute node 1206-2 is served by a second BS 1208-2, which is different from first BS 1208-1, and client device 1202 provides information derived from the service profile to first BS 1208-1, then it may be necessary for first BS 1208-1 and second BS 1208-2 to share information, or the information may be delivered by the client device to second BS 1208-2 via first BS 1208-1. This ensures that second BS 1208-2 can take the information into account when scheduling communication for compute node 1206-2. Alternatively, the information in step S1203 may be as follows: Figure 12 The information is delivered by orchestrator 1204, individually for each relevant BS, without requiring service information exchange between BSs 1208. The two mechanisms can coexist and be used in combination, depending on the accessibility of orchestrator 1204 to each BS 1208.
[0130] Figure 13 Figure 1300 illustrates an example of interaction between client device 1302, orchestrator 1304, compute node 1306, and base station 1308 containing a wireless scheduler, supporting performance monitoring and corresponding communication adjustments. These interactions are used to manage the scheduler in response to performance data monitoring during continuous compute-intensive services. Figure 13 This begins after the service is established, specifically after the offload path is established between the client device and the compute node (the compute node can be instantiated on a network node or mobile device). Figure 13As shown, an architecture involving client device 1302, orchestrator 1304 (which may also be instantiated on a network node or mobile device), compute node 1306, and BS 1308 containing a wireless scheduler is established. As illustrated in the preceding figures and description, compute node 1306 may be one of multiple compute nodes in a cluster managed by orchestrator 1304, and BS 1308 may be one of multiple BSs serving different related nodes (e.g., client device 1302 may be served by a first BS similar to BS1 1208-1, and compute node 1306 may be served by a second BS similar to BS2 1208-2). BS 1308 is responsible for the wireless scheduling of communications for client device 1302 and may optionally be responsible for the wireless scheduling of communications for compute node 1306 (e.g., if compute node 1306 is instantiated on a mobile device).
[0131] In step S1301, computation offloading occurs between client device 1302 and compute node 1306. This step can involve a bidirectional operation, where client device 1302 sends input data for a computation task to compute node 1306, and compute node 1306 returns the result of executing the computation task to client device 1302. As shown in the previous figure, the offloading path between client device 1302 and compute node 1306 can use various transmission methods (e.g., user plane data bearer, computation bearer, etc.) and can be routed via BS 1308 and / or other nodes (e.g., network nodes, lattice network nodes of communication equipment, etc.).
[0132] In step S1302, client device 1302 sends first performance data to orchestrator 1304. The first performance data may represent the performance of one or more computing tasks observed by client device 1302. For example, it may include information about the actual latency experienced by client device 1302 between transmitting one or more data packets for a computing task and receiving one or more result packets from executing the computing task, motion delays in immersive communication services, photon delays, etc. The first performance data may be considered, for example, quality of service (QoS) or quality of experience (QoE) information at the service level. It should be noted that the computing task performance observed by client device 1302 typically includes actual computing performance (e.g., the time required to execute the computing task at computing node 1306) and associated communication performance (e.g., the time it takes for messages and / or packets to propagate through the system to facilitate the execution of the computing task).
[0133] In step S1303, compute node 1306 sends second performance data to orchestrator 1304. The second performance data may represent the performance of one or more compute tasks observed by compute node 1306; for example, it may include information about the execution time of compute task instances at compute node 1306, such as the time observed between the compute node receiving data for a compute task and transmitting the results of executing the compute task. The second performance data may be considered as quality of service (QoS) information at the service level. It should be noted that the second performance data reported by compute node 1306 may not include aspects of relevant communication performance.
[0134] In step S1304, the orchestrator 1304 performs a performance evaluation based on, for example, first performance data and second performance data. The performance evaluation may consider any aspect of the first and second performance data, including comparing the two datasets. Specifically, comparing the first and second performance data for the same computational task allows the orchestrator 1304 to estimate the communication performance of the offload path between the client device 1302 and the compute node 1306.
[0135] In step S1305, orchestrator 1304 may send a communication adjustment to base station (BS) 1308, which may be derived, for example, from a performance assessment. For instance, orchestrator 1304 may determine, based on the performance assessment, that an offload path exhibits high communication latency. This situation may affect the computing service's ability to meet predefined Quality of Service (QoS) and / or Quality of Experience (QoE) targets (e.g., if compute node 1306 reports low latency in second performance data while client device 1302 reports high latency in first performance data). In this case, orchestrator 1304 may instruct BS 1308 in the communication adjustment to (attempt) schedule radio resources for lower latency, for example, by reducing the target latency previously notified to BS 1308. Alternatively, client device 1302 and / or compute node 1306 may interact with the relevant BS 1308 to enhance communication. In some embodiments, communication adjustments may include triggering the migration of client device 1302 and / or compute node 1306 from a first (serving) BS to a second (target) BS, for example, by switching to a BS expected to provide lower latency. In some embodiments, communication adjustments may include requests or instructions for prioritizing traffic associated with offloading one or more compute tasks, increasing or decreasing a target data rate (e.g., guaranteed bit rate) provided to client device 1302 and / or compute node 1306, etc. Communication between orchestrator 1304 and BS 1308 in step S1305 may employ various transmission methods, such as air interface and / or network interface, depending on the system topology, the location of orchestrator 1304 in the system, whether orchestrator 1304 is deployed on a network node or mobile device, etc.
[0136] Apart from Figure 13 In addition to the steps shown, in some embodiments, BS1308 may send one or more indications of its own status (e.g., radio status, scheduler status, congestion indicators, etc.) to orchestrator 1304 to assist in developing communication adjustments. (Steps not shown in...) Figure 13 (As shown in the diagram) This may occur, for example, before step S1305. In some cases, such as during an ongoing offloading operation for a continuous service, BS1308 may periodically or intermittently report its status to orchestrator 1304. In other cases, BS1308 may report its status based on one or more events, such as congestion metrics exceeding predefined thresholds. The information provided in the steps allows orchestrator 1304 to formulate communication adjustments to improve service performance; for example, orchestrator 1304 may determine that communication performance for task offloading is causing (or at risk of causing) the service to fail to meet one or more performance requirements. Therefore, orchestrator 1304 may request adjustments to the communication configuration, such as reducing the Packet Delay Budget (PDB), changing the expected traffic pattern, etc., to improve communication performance and better support the underlying services. In another example, if orchestrator 1304 learns that the first BS is severely congested, it may decide to switch client device 1302 and / or compute node 1306 to a second BS with lower congestion. If the orchestrator 1304 actively receives information from the BS 1308, it can anticipate the performance degradation of the service faster than waiting for the first and / or second performance data of the client device 1302 and / or the compute node 1306 to show a performance degradation.
[0137] Figure 12 and Figure 13 This involves coordination with the Radio Access Network (RAN). In such scenarios, service profiles, or information derived from service profiles, are exposed to RAN nodes (e.g., BSs) to enable optimized radio resource scheduling. For example, detailed information such as expected traffic patterns, periodicity, packet size, latency requirements, and other service-specific parameters may be provided to the BS.
[0138] While some of these parameters align with traditional Quality of Service (QoS) metrics, others (such as traffic patterns) fall outside the scope of traditional QoS definitions. BSs can utilize information based on their specific implementations because the coordination mechanism does not require standardization.
[0139] In traditional systems, the RAN is typically isolated from service information, obtaining relevant information only through the Quality of Service (QoS) profile transmitted during bearer establishment. This disclosure proposes a novel coordination mechanism that enables the RAN to access and operate based on service-specific information, thereby improving scheduling efficiency and performance. Specifically, Figure 12 The service setup phase is shown, in which the service profile is passed to the RAN, while Figure 13 This describes how service configurations are adjusted based on performance monitoring results.
[0140] Figure 14 Flowchart 1400 illustrates an example of a bearer establishment between a client device 1402 and a computing node 1406 in a network, initiated by the computing node 1406.
[0141] In some embodiments, requests for service profiles (and / or information derived therefrom) and / or management sessions or bearers may be initiated by the compute node rather than by the orchestrator 1404. Figure 14 An exemplary message flow of such an embodiment is shown, which is related to Figure 11 Similar to the previous step, the only difference lies in the initiator of the first step. After selecting compute node 1406 in step S1400, compute node 1406 (e.g., it can be one of multiple compute nodes performing different tasks related to the application) sends a request to a network node (such as an SMF or PCF, not shown in the figure) to establish a session and / or bearer for compute offloading between client device 1402 and compute node 1406. Subsequent steps are similar. Figure 11 The process is similar and conforms to the known procedures for establishing a user plane PDU session. For example, the SMF can select a UPF and trigger the creation or modification of a PDU session with the UPF and AMF, resulting in a reconfiguration operation between the AMF, service BS1408, and client device 1402. After such a session is established, client device 1402 can offload computing activities to compute node 1406, as shown in steps S1407-S1410. The session request in step S1401 may include a service profile or information derived therefrom, which can be used to configure the session / bearer to support wireless operations (e.g., scheduling of air interface transmissions) based on service requirements. This embodiment has an advantage in that compute node 1406 maintains knowledge of one or more microservices it provides, enabling compute node 1406 to automatically know the service profile of its own services.
[0142] In some embodiments, Figure 11 and / or Figure 14 The message flow can be adapted to support orchestrators and / or compute nodes hosted on mobile devices, rather than hosted on network nodes as shown in the figure. In this scenario, the session request (step S1101 or step S1401) can be implemented as an over-the-air signaling message, such as a Non-Access Stratum (NAS) message sent by the relevant mobile device to the network node (such as PCF and / or SMF) responsible for initiating session establishment. The remainder of the session establishment can proceed as shown in the figure, or according to other general procedures for establishing a communication session between client device 1402 and compute node 1406.
[0143] The process described herein uses a user plane session configuration as an example; however, as previously stated, it should be understood that the session used for compute offloading is not necessarily implemented as a user plane session (e.g., a PDU session). In some embodiments, the session or interaction used for compute offloading can be modeled as part of a “compute plane,” where the session can transfer data between client device 1402 and compute node 1406 without anchoring at the UPF. Such data transfer on the compute plane can exhibit some characteristics of user plane (UP) data transfer (e.g., the presence of communication QoS) as well as other characteristics of control plane operations (e.g., direct communication with system nodes, which may be located at peer devices, wireless nodes of the network, etc., without being associated with a PDU session of an external data network). Alternatively, communication between client device 1402 and compute node 1406 can be based on a control plane model (possibly with communication QoS parameters added to the control plane bearer), for example, meaning that compute data is encapsulated and transmitted in control plane signaling messages between client device 1402 and compute node 1406 (which may be located at a network node or peer device). In such cases, the session between compute node 1406 and client device 1402 can be managed by an upper-layer protocol, such as the protocol layer responsible for carrying compute offload data.
[0144] Figure 11 and Figure 14 The session configuration process involves coordination with the core network (CN). Specifically, orchestrator 1104 or compute node 1406 initiates a request to a CN node (such as an SMF). The request can be routed via other CN nodes (such as PCFs). If orchestrator 1104 or compute node 1406 is implemented as a user equipment (UE), the request can be communicated with the CN via NAS signaling. Upon receiving the request, the CN triggers a series of messages to establish or modify a communication session. Session configuration is driven by a service profile, which defines how the compute service should be configured or reconfigured. Orchestrator 1104 or compute node 1406 shares the necessary information with the CN to ensure the session conforms to the service profile requirements. Subsequently, the core network can configure bearers with appropriate QoS parameters and allocate resources to meet the service communication requirements.
[0145] Figure 11 and Figure 14 The message flow is basically the same, the main difference being the entity that initiates the flow. Figure 11 In the middle, the session configuration is triggered by the orchestrator 1104, while Figure 14 In this process, compute node 1406 acts as the initiator. In both cases, the initiator is from orchestrator 1104 ( Figure 11 ) or compute node 1106 ( Figure 14 All requests ultimately point to SMF, although as mentioned earlier they may be routed through intermediate nodes such as PCF.
[0146] Upon receiving a request, if a new service is being set up, the SMF performs a UPF selection. The appropriate UPF for the processing session is selected. The SMF then triggers the creation or modification of a PDU session and sends a PDU session update to the AMF. The AMF then triggers reconfiguration to the client equipment via the base station.
[0147] Once the host configuration or reconfiguration is complete, data for the computing tasks begins to flow. Data flows from the client device to the UPF, then to the compute node, and the computing results are returned from the compute node to the UPF and back to the client device.
[0148] Figure 11 and Figure 14 This framework focuses on scenarios where session configuration requests are initiated by the orchestrator or compute nodes. Beyond session establishment, it's also suitable for scenarios where the orchestrator monitors ongoing sessions involving compute offloading to compute nodes. During such monitoring, the orchestrator can identify conditions that necessitate changes to session configuration. For example, if compute node performance slows down, the bearer may need to be reconfigured to allocate less communication time (e.g., reducing packet latency budget), allowing the compute node sufficient time to complete computations. Conversely, if the compute node allocates more resources to the cluster and speeds up task execution, communication QoS requirements on the bearer can be relaxed.
[0149] In traditional systems, such session configuration requests typically originate from client devices. While configuration remains a viable solution and is currently under investigation, this disclosure focuses on scenarios where requests originate from the orchestrator or compute nodes. This approach may be particularly suitable when the orchestrator monitors compute activity and determines that the performance of the compute node requires or allows for bearer reconfiguration. For example, the orchestrator might conclude that "the performance of the compute node means that the bearer must / can be reconfigured" to meet service profile requirements.
[0150] This disclosure optimizes specific services, such as compute-intensive services, in a communication network through dynamic coordination among orchestrators, compute nodes, and client devices. For example, in a core network (CN) coordination mechanism, the orchestrator or compute node can trigger the core network to establish or modify data bearers to ensure Quality of Service (QoS) requirements. In a radio access network (RAN) coordination mechanism, scheduling assistance information can be transmitted to RAN nodes, such as base stations, enabling them to optimize radio resource scheduling based on performance requirements. Furthermore, during service operation, the performance of compute nodes can be monitored, and bearer configurations can be dynamically adjusted to maintain optimal performance. The orchestrator and compute nodes can be located in user equipment (UE), RAN cloud, or CN, supporting distributed deployment and enhancing system flexibility.
[0151] Figure 15A service profile and service quality management flowchart 1500 are shown. The process pertains to wireless communication of devices in a communication system comprising multiple nodes distributed across at least one network domain. The device is the first node among these nodes. In this disclosure, the terms "apparatus" or "device" are used to refer to any type of device, including but not limited to user equipment (UE), mobile devices, or network devices.
[0152] In step 1502, the process includes: obtaining a service profile at the first node. The service profile can define the performance requirements of the service.
[0153] Subsequently, in step 1504, the process includes: generating network domain-specific configuration information based on the service profile.
[0154] Next, in step 1506, the process includes: sending network domain-specific configuration information to a second node among multiple nodes to implement network domain-specific operations for the service. These network domain-specific operations may be related to resource allocation for the service.
[0155] In some configurations, at least one of the multiple nodes may be located on a user equipment (UE), a radio access network (RAN) element, or a core network (CN) element.
[0156] In some configurations, the first node can be an orchestrator or a compute node.
[0157] In some configurations, at least one network domain may include a Radio Access Network (RAN) domain or a Core Network (CN) domain.
[0158] In some configurations, the second node can be a scheduler node within the RAN domain, network domain-specific configuration information can include scheduling assistance information for services, and network domain-specific operations can include: the scheduler node performing scheduling on at least one of a plurality of nodes based on the scheduling assistance information.
[0159] In some configurations, the first node can generate service profiles, or it can receive service profiles from a third node among multiple nodes or from an external repository.
[0160] In some configurations, the third node can be a client node of the service.
[0161] In some configurations, a third node can correspond to a task repository. The task repository can contain images of tasks used for services.
[0162] In some configurations, the process may also include: sending assignments of tasks to be performed on compute nodes across multiple nodes.
[0163] In some configurations, the process may also include sending compute node information to client nodes among multiple nodes.
[0164] In some configurations, the first node can receive service profiles from the client nodes.
[0165] In some configurations, the process may also include sending information derived from the service profile to the compute node.
[0166] In some configurations, network domain-specific configuration information may include link utilization requirements, which may include one or any combination of traffic data rate, traffic packet size, traffic packet periodicity, and communication latency requirements.
[0167] In some configurations, multiple nodes form at least one cluster. When client devices and compute nodes within the same cluster are connected via multiple base stations (BSs), link utilization requirements can be forwarded from one BS to another.
[0168] In some configurations, the process may also include sending communication adjustment instructions to a second node to perform communication adjustments based on real-time performance monitoring feedback. For example, adjustments may relax communication quality of service (QoS) requirements when more powerful computing resources become available.
[0169] In some configurations, communication adjustment instructions may include one or any combination of the following: a changed latency target, a change in traffic priority, a change in target data rate, and a handover trigger from the serving base station (BS) to the target BS.
[0170] In some configurations, the first node can generate communication adjustment instructions based on status reports from the service BS.
[0171] In some configurations, the first node may include an orchestrator, which may generate communication adjustment instructions by receiving first performance data from a client node and second performance data from a compute node, and by evaluating the communication path between the client node and the compute node by comparing the first and second performance data.
[0172] In some configurations, the second node may include a core network (CN) node, and transmission may include delivering at least a portion of network domain-specific configuration information to the second node via another CN node.
[0173] In some configurations, the second node may include an Access and Mobility Management Function (AMF) node, and another CN node may include a Session Management Function (SMF) node or a Policy Control Function node.
[0174] In some configurations, the second node may include a CN node; network domain-specific configuration information may include requests for sessions to manage communication between client nodes and compute nodes within multiple nodes, and the requests may include information derived from the service profile; and network domain-specific operations may include triggering bearer configuration or reconfiguration for the service.
[0175] In some configurations, information derived from the service profile may include one or any combination of traffic data rate, traffic packet size, traffic periodicity, and latency requirements.
[0176] It should be understood that the specific order or hierarchy of steps in the disclosed process / flowchart is merely illustrative of the exemplary method. The specific order or hierarchy of steps in the process / flowchart may be rearranged according to design preferences. Furthermore, some steps may be combined or omitted. The appended method claims present the step elements in an exemplary order and are not limited to the specific order or hierarchy shown.
[0177] The foregoing description is intended to enable those skilled in the art to implement the various aspects described herein. Various modifications to these aspects will be readily understood by those skilled in the art, and the general principles defined herein can be applied to other aspects. Therefore, the claims are not intended to limit themselves to the aspects shown herein, but rather to be given their full scope by the language of the claims, wherein a singular reference to an element does not mean “only one” unless explicitly stated otherwise, but rather refers to “one or more.” The term “exemplary” as used herein means “as an example, instance, or illustration.” Any aspect described as “exemplary” is not necessarily to be construed as superior to or having an advantage over other aspects. Unless otherwise explicitly stated, the term “some” means one or more. Combinations such as “at least one A, B, or C,” “one or more A, B, or C,” “at least one A, B, and C,” “one or more A, B, and C,” and “A, B, C, or any combination thereof” include any combination of A, B, and / or C, and may include multiple A, multiple B, or multiple C. Specifically, combinations such as "at least one A, B, or C", "one or more A, B, or C", "at least one A, B, and C", "one or more A, B, and C", and "A, B, C, or any combination thereof" can be only A, only B, only C, A and B, A and C, B and C, or A, B, and C, wherein any such combination may include one or more members of A, B, or C. For elements of the various aspects described in this specification, all known or hereafter known to those skilled in the art structural and functional equivalents are expressly incorporated herein by reference and are intended to be covered by the claims. Furthermore, nothing disclosed herein is intended to be made public, whether or not it is expressly stated in the claims. The terms "module", "mechanism", "element", "device", etc., do not replace the word "means". Therefore, no element of a claim should be construed as means plus function unless the element is expressly described using the phrase "means for...".
Claims
1. A wireless communication method for a device in a communication system, the communication system comprising a plurality of nodes distributed in at least one network domain, the device being a first node among the plurality of nodes, the method comprising: At the first node, obtain the service profile of the service, which specifies the performance requirements of the service. This service profile is used to generate network domain-specific configuration information. as well as Send the network domain-specific configuration information to the second node among the multiple nodes to implement network domain-specific operations for the service, which are related to the resource allocation of the service.
2. The method of claim 1, wherein at least one of the plurality of nodes is located on a user equipment, on a wireless access network element, or on a core network element.
3. The method of claim 1, wherein the first node is an orchestrator or a compute node.
4. The method of claim 1, wherein the at least one network domain includes a wireless access network domain or a core network domain.
5. The method of claim 4, wherein the second node is a scheduler node within the radio access network domain, the network domain-specific configuration information includes scheduling assistance information for the service, and the network domain-specific operation includes: The scheduler node performs scheduling for at least one of the plurality of nodes based on the scheduling assistance information.
6. The method of claim 1, wherein the first node generates the service profile or receives the service profile from a third node among the plurality of nodes or an external repository.
7. The method of claim 6, wherein the third node is a client node of the service.
8. The method of claim 6, wherein the third node corresponds to a task repository, and the task repository contains images of tasks for the service.
9. The method of claim 1, further comprising: Send the task of executing the service to the compute nodes among the multiple nodes.
10. The method of claim 9, further comprising: Send the information of the compute node to the client node among the multiple nodes.
11. The method of claim 10, wherein the first node receives the service profile from the client node.
12. The method of claim 9, further comprising: Send the information derived from the service profile to the computing node.
13. The method of claim 1, wherein the network domain-specific configuration information includes link utilization requirements, and the link utilization requirements include one or any combination of traffic data rate, traffic packet size, traffic packet periodicity and communication latency requirements.
14. The method of claim 13, wherein the plurality of nodes form at least one cluster, and wherein when client devices and computing nodes within the same cluster are connected via a plurality of base stations, the link utilizes a request to forward from one of the plurality of base stations to another base station.
15. The method of claim 10, further comprising: Send a communication adjustment command to the second node to perform communication adjustments based on real-time performance monitoring feedback.
16. The method of claim 15, wherein the communication adjustment instruction comprises: The change is triggered by one or any combination of the following: a change in latency target, a change in traffic priority, a change in target data rate, and a handover trigger from the serving base station to the target base station.
17. The method of claim 16, wherein the first node generates the communication adjustment instruction based on a status report from the serving base station.
18. The method of claim 15, wherein the first node includes an orchestrator, and the orchestrator generates the communication adjustment instruction in the following manner: Receive first performance data from the client node and second performance data from the computing node; and The communication path between the client node and the compute node is evaluated by comparing the first performance data and the second performance data.
19. The method of claim 1, wherein the second node includes a core network node, and the transmission includes: At least a portion of the network domain-specific configuration information is delivered to the second node via another core network node.
20. The method of claim 19, wherein the second node includes an access and mobility management function node, and the other core network node includes a session management function node or a policy control function node.
21. The method of claim 4, wherein the second node includes a core network node; the network domain-specific configuration information includes requests for managing sessions of communication between client nodes and compute nodes within the plurality of nodes, the requests including information derived from the service profile; and the network domain-specific operation includes: Trigger a bearer configuration or reconfiguration for this service.
22. The method of claim 21, wherein the information derived from the service profile includes one or any combination of traffic data rate, traffic packet size, traffic periodicity, and latency requirements.
23. An apparatus for wireless communication, the apparatus being a first node among a plurality of nodes included in a communication system, the plurality of nodes being distributed in at least one network domain, the apparatus comprising: Memory; as well as At least one processor coupled to the memory is configured as follows: Obtain the service profile for the service, which specifies the performance requirements for the service; This service profile is used to generate network domain-specific configuration information. as well as Send the network domain-specific configuration information to the second node among the multiple nodes to implement network domain-specific operations for the service, which are related to the resource allocation of the service.
24. A computer-readable medium storing computer-executable code for wireless communication of a device, the device being a first node among a plurality of nodes included in a communication system, the plurality of nodes being distributed in at least one network domain, the computer-readable medium including code for: Obtain the service profile for the service, which specifies the performance requirements for the service; Generate network domain-specific configuration information based on this service profile; and Send the network domain-specific configuration information to the second node among the multiple nodes to implement network domain-specific operations for the service, which are related to the resource allocation of the service.
