Collaborative task completion in wireless communication systems
By enabling collaboration between core networks and base stations for UE selection and resource allocation, the challenges of QoS guarantee and UE selection in federated learning are addressed, enhancing the efficiency of collaborative task completion in wireless networks.
Patent Information
- Application Number
- PCT/CN2024/072149
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-01-12
- Publication Date
- 2025-07-17
AI Technical Summary
Current wireless networks face challenges in enhancing Quality-of-Service (QoS) guarantee mechanisms and UE selection for federated learning, as well as efficient task completion in collaborative systems like UAV search and rescue, due to limitations in data aggregation and real-time resource management.
Implementing methods where a core network and base station collaborate to select and allocate resources for UEs based on real-time information exchange, including task identifiers, traffic patterns, and resource availability, to enhance federated learning and task completion efficiency.
Improves the learning iteration speed and resource allocation efficiency by leveraging base station knowledge for UE selection and scheduling, optimizing the QoS guarantee mechanism for collaborative tasks.
Smart Images

Figure CN2024072149_17072025_PF_FP_ABST
Abstract
Description
COLLABORATIVE TASK COMPLETION IN WIRELESS COMMUNICATION SYSTEMSTECHNICAL FIELD
[0001] This disclosure is directed generally to digital wireless communications.BACKGROUND
[0002] Mobile telecommunication technologies are moving the world toward an increasingly connected and networked society. In comparison with the existing wireless networks, next generation systems and wireless communication techniques will need to support a much wider range of use-case characteristics and provide a more complex and sophisticated range of access requirements and flexibilities.
[0003] Long-Term Evolution (LTE) is a standard for wireless communication for mobile devices and data terminals developed by 3rd Generation Partnership Project (3GPP) . LTE Advanced (LTE-A) is a wireless communication standard that enhances the LTE standard. The 5th generation of wireless system, known as 5G, advances the LTE and LTE-Awireless standards and is committed to supporting higher data-rates, large number of connections, ultra-low latency, high reliability and other emerging business needs.SUMMARY
[0004] Techniques are disclosed for completing tasks based on the collaboration between multiple nodes in a wireless network. The described embodiments are applicable to federated learning, as well as joint task completion using unmanned robots, e.g., UAVs or drones.
[0005] In an example aspect, a wireless communication method includes transmitting, by a core network to a network node, information associated with a task, and then receiving, from the network node, a list of wireless devices. In this example, the list of wireless devices is determined based on at least the information.
[0006] In another example aspect, a wireless communication method includes receiving, by a network node from a core network, information associated with a task, and then transmitting, to the core network, a list of wireless devices. In this example, the list of wireless devices is determined based on at least the information.
[0007] In yet another example aspect, the above-described methods are embodied in the form of processor-executable code and stored in a non-transitory computer-readable storage medium. The code included in the computer readable storage medium when executed by a processor, causes the processor to implement the methods described in this patent document.
[0008] In yet another example aspect, a device that is configured or operable to perform the above-described methods is disclosed.
[0009] The above and other aspects and their implementations are described in greater detail in the drawings, the descriptions, and the claims.
[0010] BRIEF DESCRIPTION OF THE DRAWING
[0011] FIGS. 1A and 1B show flowcharts for example wireless communication methods.
[0012] FIG. 2 shows a block diagram of an example hardware platform that may be a part of a network device or a communication device.
[0013] FIG. 3 shows an example of wireless communication including a base station (BS) and user equipment (UE) based on some implementations of the disclosed technology.DETAILED DESCRIPTION
[0014] In today's rapidly evolving technological landscape, artificial intelligence (AI) has become one of the most revolutionary technologies, and is expected to have a significant impact on human society. Over the past few years, advancements in AI-related theoretical research, technological innovation, and software and hardware upgrades have greatly propelled the development of the AI industry.
[0015] Entering 2022, large AI models such as ChatGPT have exploded in popularity worldwide, and artificial intelligence-generated content (AIGC) has sparked a new wave of enthusiasm. The public's interest in artificial intelligence has deepened, and AI has become a significant force in global technological and industrial development. As the commercialization of artificial intelligence accelerates, a burgeoning era of AI is on the horizon.
[0016] Data is crucial for the development of artificial intelligence because it contains important patterns, such as human biometric traits, preferences, financial credit, etc. Artificial intelligence technology can mine these patterns from the data. These trained AI models have been applied in various industries, such as clinical auxiliary diagnosis in the medical field, facial recognition in the security industry, and so on. In these applications, the accuracy of the model is vital, and the precision of the model depends on the training data. Only through training with a large amount of data can models that operate consistently with high accuracy be obtained.
[0017] However, the development of artificial intelligence is currently facing a data dilemma. Although a large amount of data has been accumulated in various industries with the development of the information society, this data is held by different entities. Due to restrictions on data privacy, security, and legal and policy supervision, they cannot be effectively aggregated, which restricts the improvement of AI model performance.
[0018] In response to the data dilemma, the concept of federated learning has been proposed. Essentially, federated learning is a distributed machine learning framework. Its core idea is that data does not leave the local site, and multiple data sources participate in model training together. Without the need for transferring the original data, only intermediate parameters of the model are exchanged for joint model training. The current federated learning models are divided into client / server models and decentralized models. Most current federated learning systems are based on the client / server model, which fundamentally involves collaborative distributed computing under the guidance of a central node. The central node assists other computing nodes in local model updates, distributes computing tasks, and aggregates and computes the final model results.
[0019] However, current wireless networks, despite supporting federated learning services, still face some significant challenges.
[0020] For example, the learning iteration speed of the client / server model depends on the computation time of each participating node and the time taken to feedback computation results. Since the current wireless communication system's Quality-of-Service (QoS) guarantee mechanism cannot perform business feature perception, there may be a situation where a slower computing node impacts the learning efficiency of federated learning. To better serve federated learning services, enhancing the QoS guarantee mechanism, perceiving business features, and making better scheduling strategies specifically for federated learning are being considered.
[0021] In addition to the QoS guarantee mechanism, the UE selection mechanism is also being investigated. In general, a computing node will be selected by the core network or the application server. However, a base station typically knows a lot of information regarding UEs that the core network and / or application server does not know (e.g., the usage of transmission resources, the channel status of UEs, and the like) . Thus, how to leverage base stations to select more suitable UEs to perform federated learning is being considered.
[0022] In addition to federated learning, there are many examples of the joint completion of tasks, e.g., multiple robots, UAV collaborative search and rescue, and the like. Thus, solutions for federated learning are being implemented in systems with multiple nodes that collaborate to complete tasks. Embodiments of the disclosed technology are directed to methods and systems that support the collaborative completion of tasks by multiple nodes.
[0023] The example headings for the various sections below are used to facilitate the understanding of the disclosed subject matter and do not limit the scope of the claimed subject matter in any way. Accordingly, one or more features of one example section can be combined with one or more features of another example section. Furthermore, 5G terminology is used for the sake of clarity of explanation, but the techniques disclosed in the present document are not limited to 5G technology only, and may be used in wireless systems that implemented other protocols. For example, some embodiments have been described using interactions between a core network and a base station. However, the described embodiments are applicable to other network functions and / or entities, e.g., the application server in the core network, that are communicating with the base station.
[0024] Examples of UE selection for collaborative task completion
[0025] In some embodiments, a core network is configured to select one or more UE for task completion via collaboration. Alternatively, a base station may be configured for UE selection.
[0026] Core network selecting the UE
[0027] In some embodiments, and since a base station typically knows a lot of information regarding UEs that the core network does not know (e.g., usage of transmission resources, channel status of UEs, and the like) , the base station is configured to provide the core network with a list of candidate UEs, which can assist the core network in selecting the UE.
[0028] In some examples, the core network provides a task identifier, which UE has joined the task, and the traffic pattern associated with the task to the base station. The base station uses this additional information to generate the list of candidate UEs.
[0029] In some examples, the base station provides, based on the information it knows, the candidate UE list and a task identifier to the core network. The final UE list, which is determined by the core network based on the candidate UE list, includes those UEs that have been selected to collaborate for completion of a task associated with the task identifier that was provided by the base station. The core network transmits the final UE list to the base station. The base station performs resource allocation based on the final UE list, the traffic pattern of data associated with the task, and the traffic pattern associated with the data results from the task.
[0030] Base station selecting the UE
[0031] In some embodiments, and since usage of transmission resources, channel status of UEs, and other parameters change in real time, the base station (which typically has knowledge of such information) can be configured to select the appropriate UEs to assist in completion of the task, and determine the final UE list.
[0032] In some examples, the core network provides a task identifier, which UE has joined the task, and the traffic pattern associated with the task to the base station. The base station uses this additional information to generate the final UE list, which is then transmitted to the core network along with the task identifier.
[0033] In some examples, the base station transmits the final UE list and a task identifier of the task to the core network. The base station performs resource allocation based on the final UE list, the traffic pattern of data associated with the task, and the traffic pattern associated with the data results from the task.
[0034] In some examples, and upon determining that there is an update associated with the UEs that are assisting in completing the task, the base station is configured to transmit the task identifier and updated information for the final UE list to the core network. Additionally, when the updated information for the final UE list is transmitted by the base station to the core network, it may be accompanied by a reason for the update.
[0035] Examples of auxiliary information from the core network
[0036] Embodiments of the disclosed technology enable a core network to provide auxiliary (or assistance) information to the base station, thereby better facilitating scheduling.
[0037] Notifying the base station of which UEs have joined the task
[0038] In some embodiments, the core network is configured to provide a task identifier of the task to the base station. In order to allow the base station to select one or more suitable UEs to complete the task, the core network is further configured to provide a list of tasks that any particular UE has joined to the base station.
[0039] Determining the traffic pattern of the task data delivered to the UE
[0040] In some embodiments, the core network is configured to deliver, to the base station, the traffic pattern of task data delivered to the UE. In some examples, this traffic pattern information includes at least one of:
[0041] – the periodicity of task data delivered to the UE, e.g., how often does the UE receive data related to the completion of the task?
[0042] – the amount of task data, e.g., in bits or bytes, delivered to the UE.
[0043] – the Quality-of-Service (QoS) requirement of the task; for example, the QoS requirement could be the QoS flows associated with the task that are delivered to the UE, or the delay requirement of the task data delivered to the UE, e.g., the maximum time deviation of task data delivered to multiple UEs that jointly complete the task.
[0044] Determining the traffic pattern of data results provided by the UE
[0045] In some embodiments, the core network is configured to deliver, to the base station, the traffic pattern of data results that the UE needs to provide upon completion of the task. In some examples, this traffic pattern information includes at least one of:
[0046] – the periodicity of data results provided by the UE, e.g., how often does the UE generate data results? How often should the UE transmit the data results?
[0047] – the amount of data results, e.g., in bits or bytes, upon completion of the task.
[0048] – the Quality-of-Service (QoS) requirement of the data results; for example, the QoS requirement could be the delay requirement of the data results provided by the UE, e.g., the maximum time deviation of data provided by multiple UEs that jointly complete the task.
[0049] Transmitting assistance information
[0050] In some embodiments, other assistance information transmitted by the core network to the base station includes (i) the relationship between resources used (e.g., computing resource, transmission resource, etc. ) and the time it takes to complete the task, and / or (ii) the energy consumption limit to complete the task.
[0051] Examples of auxiliary information from the wireless device
[0052] Embodiments of the disclosed technology enable a UE to provide auxiliary (or assistance) information to the base station, thereby allowing the base station to select the appropriate UEs to complete the task.
[0053] Transmitting assistance information
[0054] In some embodiments, the assistance information transmitted by the UE, to the base station, includes (i) the available resources (e.g., computing resources, storage resources, etc. ) owned by the UE, and / or (ii) the energy consumption efficiency of UE when completing tasks.
[0055] Transmitting a feedback report on the UE’s data generation time
[0056] In certain scenarios, the data arrival time at the UE upon task completion may be earlier than the uplink transmission time allocated by the base station.
[0057] In some embodiments, to enable the base station to schedule transmission resources more efficiently and to allow the UE to transmit results earlier, a UE is configured to generate a feedback report about the task and provide the feedback report to the base station. In some examples, the feedback report includes (i) a data arrival time at the UE upon task completion, and / or (ii) the time gap between the data arrival time and a reference time. In some examples, the reference time corresponds to a grant allocated by the base station or an uplink transmission time. In other examples, the reference time corresponds to the transmission time of a semi-persistent scheduling (SPS) mechanism or a discontinuous reception (DRX) mechanism.
[0058] Example methods and implementations of the disclosed technology
[0059] FIG. 1A shows a flowchart for an example wireless communication method 100. The method 100 includes, at operation 102, transmitting, by a core network to a network node, information associated with a task.
[0060] The method 100 includes, at operation 104, receiving, from the network node, a list of wireless devices that is determined based on at least the information.
[0061] FIG. 1B shows a flowchart for an example wireless communication method 150. The method 150 includes, at operation 152, receiving, by a network node from a core network, information associated with a task.
[0062] The method 150 includes, at operation 154, transmitting, to the core network, a list of wireless devices that is determined based on at least the information.
[0063] The described features can be implemented to further provide one or more of the following technical solutions:
[0064] 1. A wireless communication method, comprising: transmitting, by a core network to a network node, information associated with a task; and receiving, from the network node, a list of wireless devices, wherein the list of wireless devices is determined based on at least the information.
[0065] 2. A wireless communication method, comprising: receiving, by a network node from a core network, information associated with a task; and transmitting, to the core network, a list of wireless devices, wherein the list of wireless devices is determined based on at least the information.
[0066] 3. The method of solution 1 or 2, wherein the network node is configured to determine the list of wireless devices corresponding to a final list of wireless devices configured to assist in a completion of the task.
[0067] 4. The method of solution 3, wherein the network node is configured to transmit, to the core network, an update associated with the final list of wireless devices and a reason for the update.
[0068] 5. The method of solution 1 or 2, wherein the list of wireless devices corresponds to a list of candidate wireless devices configured to assist in a completion of the task, wherein the core network is configured to: transmit, to the network node, the final list of wireless devices.
[0069] 6. The method of any of solutions 3 to 5, wherein the network node is configured to allocate resources based on the final list of wireless devices and the information associated with the task.
[0070] 7. The method of any of solutions 3 to 6, wherein the task comprises a federated learning process that is completed based on assistance from each of the final list of wireless devices.
[0071] 8. The method of any of solutions 3 to 7, wherein the core network is configured to transmit, to the network node, a traffic pattern associated with the task, and wherein the traffic pattern comprises at least one of: a periodicity of data associated with the task delivered to a wireless device from the final list of wireless devices, a size of the data associated with the task delivered to the wireless device, or a quality-of-service (QoS) requirement associated with the task.
[0072] 9. The method of solution 8, wherein the QoS requirement includes a delay requirement comprising a maximum time deviation of the data associated with the task being delivered to each of the final list of wireless devices.
[0073] 10. The method of any of solutions 3 to 7, wherein the core network is configured to transmit, to the network node, a traffic pattern associated with results provided by a wireless device at the completion of the task, and wherein the traffic pattern comprises at least one of: a periodicity of the results, a size of the results, or a quality-of-service (QoS) requirement associated with the results.
[0074] 11. The method of solution 10, wherein the QoS requirements includes a delay requirement comprising a maximum time deviation of the results provided by each of the final list of wireless devices.
[0075] 12. The method of any of solutions 3 to 7, wherein the core network is configured to transmit, to the network node, assistance information associated with the task, and wherein the assistance information comprises at least one of: a relationship between resources used in the completion of the task and a time taken for the completion of the task, or an energy consumption limit associated with the completion of the task.
[0076] 13. The method of any of solutions 3 to 7, wherein at least one wireless device is configured to transmit, to the network node, assistance information associated with the task, and wherein the assistance information comprises at least one of: available resources owned by the at least one wireless device, or an energy consumption efficiency of the at least one wireless device associated with assisting in the completion of the task.
[0077] 14. The method of any of solutions 3 to 7, wherein at least one wireless device is configured to transmit, to the network node, a feedback report comprising at least one of: a time corresponding to an arrival of data associated with the task, or a time gap between the time corresponding to the arrival of the data and an allocated transmission time.
[0078] 15. The method of solution 14, wherein the allocated transmission time corresponds to an allocated grant and / or an uplink transmission time.
[0079] 16. The method of solution 14, wherein the allocated transmission time corresponds to a transmission time of a semi-persistent scheduling (SPS) mechanism or a discontinuous reception (DRX) mechanism.
[0080] 17. An apparatus for wireless communication comprising a processor, configured to implement a method recited in one or more of solutions 1 to 16.
[0081] 18. A non-transitory computer readable program storage medium having code stored thereon, the code, when executed by a processor, causing the processor to implement a method recited in one or more of solutions 1 to 16.
[0082] FIG. 2 shows a block diagram of an example hardware platform 200 that may be a part of a network device (e.g., base station) or a communication device (e.g., a user equipment (UE) ) . The hardware platform 200 includes at least one processor 210 and a memory 205 having instructions stored thereupon. The instructions upon execution by the processor 210 configure the hardware platform 200 to perform the operations described in FIGS. 1A and 1B, and in the various embodiments described in this patent document. The transmitter 215 transmits or sends information or data to another device. For example, a network device transmitter can send a message to a user equipment. The receiver 220 receives information or data transmitted or sent by another device. For example, a user equipment can receive a message from a network device.
[0083] The implementations as discussed above will apply to a wireless communication. FIG. 3 shows an example of a wireless communication system (e.g., a 5G or NR cellular network) that includes a base station 320 and one or more user equipment (UE) 311, 312 and 313. In some embodiments, the UEs access the BS (e.g., the network) using a communication link to the network (sometimes called uplink direction, as depicted by dashed arrows 331, 332, 333) , which then enables subsequent communication (e.g., shown in the direction from the network to the UEs, sometimes called downlink direction, shown by arrows 341, 342, 343) from the BS to the UEs. In some embodiments, the BS send information to the UEs (sometimes called downlink direction, as depicted by arrows 341, 342, 343) , which then enables subsequent communication (e.g., shown in the direction from the UEs to the BS, sometimes called uplink direction, shown by dashed arrows 331, 332, 333) from the UEs to the BS. The UE may be, for example, a smartphone, a tablet, a mobile computer, a machine to machine (M2M) device, an Internet of Things (IoT) device, and so on.
[0084] Some of the embodiments described herein are described in the general context of methods or processes, which may be implemented in one embodiment by a computer program product, embodied in a computer-readable medium, including computer-executable instructions, such as program code, executed by computers in networked environments. A computer-readable medium may include removable and non-removable storage devices including, but not limited to, Read Only Memory (ROM) , Random Access Memory (RAM) , compact discs (CDs) , digital versatile discs (DVD) , etc. Therefore, the computer-readable media can include a non-transitory storage media. Generally, program modules may include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Computer-or processor-executable instructions, associated data structures, and program modules represent examples of program code for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps or processes.
[0085] Some of the disclosed embodiments can be implemented as devices or modules using hardware circuits, software, or combinations thereof. For example, a hardware circuit implementation can include discrete analog and / or digital components that are, for example, integrated as part of a printed circuit board. Alternatively, or additionally, the disclosed components or modules can be implemented as an Application Specific Integrated Circuit (ASIC) and / or as a Field Programmable Gate Array (FPGA) device. Some implementations may additionally or alternatively include a digital signal processor (DSP) that is a specialized microprocessor with an architecture optimized for the operational needs of digital signal processing associated with the disclosed functionalities of this application. Similarly, the various components or sub-components within each module may be implemented in software, hardware or firmware. The connectivity between the modules and / or components within the modules may be provided using any one of the connectivity methods and media that is known in the art, including, but not limited to, communications over the Internet, wired, or wireless networks using the appropriate protocols.
[0086] While this document contains many specifics, these should not be construed as limitations on the scope of an invention that is claimed or of what may be claimed, but rather as descriptions of features specific to particular embodiments. Certain features that are described in this document in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a sub-combination or a variation of a sub-combination. Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results.
[0087] Only a few implementations and examples are described and other implementations, enhancements and variations can be made based on what is described and illustrated in this disclosure.
Claims
1.A wireless communication method, comprising:transmitting, by a core network to a network node, information associated with a task; andreceiving, from the network node, a list of wireless devices,wherein the list of wireless devices is determined based on at least the information.2.A wireless communication method, comprising:receiving, by a network node from a core network, information associated with a task; andtransmitting, to the core network, a list of wireless devices,wherein the list of wireless devices is determined based on at least the information.3.The method of claim 1 or 2, wherein the network node is configured to determine the list of wireless devices corresponding to a final list of wireless devices configured to assist in a completion of the task.4.The method of claim 3, wherein the network node is configured to transmit, to the core network, an update associated with the final list of wireless devices and a reason for the update.5.The method of claim 1 or 2, wherein the list of wireless devices corresponds to a list of candidate wireless devices configured to assist in a completion of the task, wherein the core network is configured to:transmit, to the network node, the final list of wireless devices.6.The method of any of claims 3 to 5, wherein the network node is configured to allocate resources based on the final list of wireless devices and the information associated with the task.7.The method of any of claims 3 to 6, wherein the task comprises a federated learning process that is completed based on assistance from each of the final list of wireless devices.8.The method of any of claims 3 to 7, wherein the core network is configured to transmit, to the network node, a traffic pattern associated with the task, and wherein the traffic pattern comprises at least one of:a periodicity of data associated with the task delivered to a wireless device from the final list of wireless devices,a size of the data associated with the task delivered to the wireless device, ora quality-of-service (QoS) requirement associated with the task.9.The method of claim 8, wherein the QoS requirement includes a delay requirement comprising a maximum time deviation of the data associated with the task being delivered to each of the final list of wireless devices.10.The method of any of claims 3 to 7, wherein the core network is configured to transmit, to the network node, a traffic pattern associated with results provided by a wireless device at the completion of the task, and wherein the traffic pattern comprises at least one of:a periodicity of the results,a size of the results, ora quality-of-service (QoS) requirement associated with the results.11.The method of claim 10, wherein the QoS requirements includes a delay requirement comprising a maximum time deviation of the results provided by each of the final list of wireless devices.12.The method of any of claims 3 to 7, wherein the core network is configured to transmit, to the network node, assistance information associated with the task, and wherein the assistance information comprises at least one of:a relationship between resources used in the completion of the task and a time taken for the completion of the task, oran energy consumption limit associated with the completion of the task.13.The method of any of claims 3 to 7, wherein at least one wireless device is configured to transmit, to the network node, assistance information associated with the task, and wherein the assistance information comprises at least one of:available resources owned by the at least one wireless device, oran energy consumption efficiency of the at least one wireless device associated with assisting in the completion of the task.14.The method of any of claims 3 to 7, wherein at least one wireless device is configured to transmit, to the network node, a feedback report comprising at least one of:a time corresponding to an arrival of data associated with the task, ora time gap between the time corresponding to the arrival of the data and an allocated transmission time.15.The method of claim 14, wherein the allocated transmission time corresponds to an allocated grant and / or an uplink transmission time.16.The method of claim 14, wherein the allocated transmission time corresponds to a transmission time of a semi-persistent scheduling (SPS) mechanism or a discontinuous reception (DRX) mechanism.17.An apparatus for wireless communication comprising a processor, configured to implement a method recited in one or more of claims 1 to 16.18.A non-transitory computer readable program storage medium having code stored thereon, the code, when executed by a processor, causing the processor to implement a method recited in one or more of claims 1 to 16.
Citation Information
Patent Citations
Measuring method and device
CN103686823A
Abnormal working terminal processing method and device, and abnormal working terminal identifying method and device
CN109391933A
System, method and apparatus for ad-hoc utilization of available resources across mobile devices
US20170367086A1
Multi-device collaboration control method and apparatus, and readable storage medium
WO2023226030A1