Carrier configuration method and apparatus, and electronic device

Abstract

The carrier configuration method and device and electronic equipment provided by the application relate to the technical field of wireless communication, can comprehensively perceive the dynamic characteristics of a heterogeneous network scene by collecting multi-dimensional state information covering a communication terminal, a network environment and network load. A strategy set containing multiple candidate carrier combinations and transmission modes is generated based on the characteristics of the communication terminal, which provides a selection space for carrier configuration. Through a preset intelligent decision model, an optimal target dynamically adapted to different service types is used to make a joint selection decision from the candidate configuration strategy set, so that accurate matching between carrier resource configuration and actual service demand of the terminal is realized. Therefore, the application can actively adapt to the dynamic changes of the network environment and the mixed services, effectively meet the differentiated performance requirements of throughput, delay and reliability of diversified services, and improve the resource utilization efficiency and overall service performance.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a carrier configuration method and apparatus, and an electronic device. Background Technology

[0002] With the development of wireless communication technology, in order to meet the large-scale traffic demand and diversified service types, such as enhanced mobile broadband services, ultra-reliable low-latency communication services, and massive machine-type communication services, it is necessary to improve the system spectrum efficiency and throughput through carrier aggregation technology. Carrier aggregation technology is one of the key capabilities supported by terminals.

[0003] However, carrier allocation methods in related technologies typically employ relatively simplistic strategies. For example, they may allocate carriers to terminal devices based on real-time load conditions, aiming for load balancing; or they may select carriers solely based on instantaneous channel quality, lacking a comprehensive consideration of service requirements. Therefore, these carrier allocation methods lack the ability to perceive and differentiate heterogeneous network scenarios, cannot achieve precise matching of resources and demands, and their decision-making mechanisms are mostly passive responses based on fixed rules, making them ill-suited to adapt to dynamically changing network environments and services.

[0004] Therefore, how to accurately configure carriers to meet the diverse data transmission performance requirements of various services in heterogeneous network scenarios is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a carrier configuration method, apparatus, and electronic device. Its main objective is to address the problem of how to accurately configure carriers to meet the diverse data transmission performance requirements of various services in heterogeneous network scenarios.

[0006] According to a first aspect of this application, a carrier configuration method is provided, comprising:

[0007] Collect multi-dimensional status information in the current communication scenario, including communication terminal characteristics, network environment characteristics, and network load characteristics; Based on the characteristics of the communication terminal, a candidate configuration strategy set is selected from multiple available carriers in the current communication scenario. The candidate configuration strategy set includes multiple candidate carrier configuration strategies, and each candidate carrier configuration strategy includes at least a combination of candidate carriers and a carrier transmission mode. Based on multidimensional state information, a target carrier configuration strategy is jointly selected for the communication terminal in the current communication scenario from the candidate configuration strategy set through a preset intelligent decision model. The optimization objective of the intelligent decision model is dynamically adapted according to the service type of the communication terminal. Configure the corresponding carrier resources and carrier transmission parameters for the communication terminal according to the target carrier configuration strategy.

[0008] According to a second aspect of this application, a carrier configuration apparatus is provided, comprising: The acquisition unit is used to acquire multi-dimensional status information, including communication terminal characteristics, network environment characteristics, and network load characteristics, under the current communication scenario. The first selection unit is used to select a set of candidate configuration strategies from multiple available carriers in the current communication scenario based on the characteristics of the communication terminal. The set of candidate configuration strategies includes multiple candidate carrier configuration strategies, and each candidate carrier configuration strategy includes at least a combination of candidate carriers and a carrier transmission mode. The second selection unit is used to jointly select a target carrier configuration strategy for the communication terminal in the current communication scenario based on multi-dimensional state information and a preset intelligent decision model from the candidate configuration strategy set. The optimization objective of the intelligent decision model is dynamically adapted according to the service type of the communication terminal. The configuration unit is used to configure the corresponding carrier resources and carrier transmission parameters for the communication terminal according to the target carrier configuration strategy.

[0009] According to a third aspect of this application, an electronic device is provided, comprising: At least one processor; and A memory that is communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor, such that the at least one processor is able to perform the method described in the first aspect above.

[0010] According to a fourth aspect of this application, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the method of the first aspect described above.

[0011] According to a fifth aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method as described in the first aspect above.

[0012] The carrier configuration method, apparatus, and electronic equipment provided in this application can comprehensively perceive the dynamic characteristics of heterogeneous network scenarios by collecting multi-dimensional state information covering communication terminals, network environment, and network load. Based on the characteristics of the communication terminals, a strategy set containing multiple candidate carrier combinations and transmission modes is generated, providing a selection space for carrier configuration. Through a preset intelligent decision-making model, and based on optimization objectives dynamically adapted to different service types, a joint selection decision is made from the candidate configuration strategy set, thereby achieving precise matching between carrier resource configuration and the actual service needs of the terminal. Therefore, this application can proactively adapt to the dynamic changes of mixed network environment and services, solving the problem of single carrier configuration strategies and inability to achieve precise matching of resources and needs in related technologies. It effectively meets the differentiated performance requirements of diverse services for throughput, latency, and reliability, improving resource utilization efficiency and overall service performance.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0014] The accompanying drawings are provided for a better understanding of this solution and do not constitute a limitation of this application. Wherein: Figure 1 This is a flowchart illustrating a carrier configuration method provided in an embodiment of this application. Figure 2 This is a flowchart illustrating another carrier configuration method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a carrier configuration device provided in an embodiment of this application; Figure 4 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0015] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0016] This application relates to the field of wireless communication technology, and in particular to a method for carrier configuration in a heterogeneous network scenario containing multiple different types of communication nodes.

[0017] The carrier configuration method of this application transforms the traditional static resource allocation process into a dynamic process capable of cross-layer joint decision-making. This application achieves closed-loop optimization by executing integrated steps in the control unit on the base station or network side, precisely adapting to complex communication scenarios and diverse service requirements.

[0018] The carrier configuration method, apparatus, and electronic device of this application are described below with reference to the accompanying drawings.

[0019] Figure 1 This is a flowchart illustrating a carrier configuration method provided in an embodiment of this application.

[0020] like Figure 1 As shown, the method includes the following steps: Step 101: Collect multi-dimensional status information in the current communication scenario, including communication terminal characteristics, network environment characteristics, and network load characteristics.

[0021] In the embodiments of this application, multidimensional state information is a comprehensive set of features used to fully characterize various aspects affecting communication performance. Multidimensional state information includes, but is not limited to, features in three dimensions: communication terminal features, network environment features, and network load features.

[0022] Communication terminal characteristics refer to attributes related to the user equipment (i.e., the communication terminal) itself and its services, such as: the type of terminal (eMBB terminal, Ultra-Reliable Low Latency Communications (URLLC) terminal, or Massive Machine Type Communications (mMTC) terminal), the type of service currently initiated by the terminal, the Quality of Service (QoS) requirements of the service (e.g., latency limit, minimum guaranteed rate, maximum tolerable block error rate), and the terminal's own radio frequency and protocol stack capabilities (e.g., the maximum number of carrier aggregations supported, the bandwidth supported, and the number of Multiple-Input Multiple-Output (MIMO) layers).

[0023] Network environment characteristics refer to the propagation conditions of the wireless channel itself in the current communication scenario. They are obtained by measuring all available candidate carriers (i.e., available carriers) in the current communication scenario, including but not limited to Channel State Information (CSI), Reference Signal Received Power (RSRP), Signal to Interference plus Noise Ratio (SINR), and other indicators reflecting channel quality, i.e., channel state.

[0024] Network load characteristics reflect the occupancy and congestion level of network resources, such as: the physical resource block utilization of each available candidate carrier, the number of users (number of communication terminals) currently receiving services on this candidate carrier, and the average waiting time of data packets in the transmission queue.

[0025] Specifically, the content of multidimensional state information can be illustrated using examples, but is not limited to, Table 1 below: Table 1

[0026] By collecting and fusing information from multiple dimensions in real time, a multi-dimensional state information space that can reflect the overall operating status of the network at the current moment is constructed.

[0027] Step 102: Select a set of candidate configuration strategies from multiple available carriers in the current communication scenario based on the characteristics of the communication terminal. The set of candidate configuration strategies includes multiple candidate carrier configuration strategies, and each candidate carrier configuration strategy includes at least a combination of candidate carriers and a carrier transmission mode.

[0028] In the embodiments of this application, the candidate configuration strategy set is a dynamically generated set of carrier configuration strategies. The composition of this candidate configuration strategy set is not fixed, but is selected and generated based on the specific communication terminal characteristics (especially the terminal's hardware and protocol capabilities, i.e., terminal capabilities).

[0029] Each candidate carrier configuration strategy is an element in the candidate configuration strategy set, and each candidate carrier configuration strategy contains at least two key components: candidate carrier combination and carrier transmission mode. Candidate carrier combination refers to a specific combination of one or more carriers selected from all available carriers based on terminal capabilities (such as the maximum number of aggregated carriers). For example, selecting carrier one and carrier two for aggregation, or selecting carrier one, carrier two, and carrier three for aggregation. When selecting candidate carrier combinations, the complementary characteristics of carriers in different frequency bands are fully considered.

[0030] The carrier transmission mode is the specific physical layer transmission parameter scheme configured for each carrier in the selected candidate carrier combination. This mainly includes MIMO operating modes (e.g., transmit diversity, spatial multiplexing or beamforming, multi-user MIMO), modulation and coding scheme (MCS) level, and power allocation scheme among multiple aggregated carriers.

[0031] In other words, when constructing the candidate carrier configuration set, a dynamic candidate policy set available at the current moment is generated based on the collected user equipment (UE) characteristics (especially UE capabilities). Each candidate policy is a tuple (carrier combination, transmission mode).

[0032] The carrier combination and transmission mode can be illustrated using examples, but are not limited to, those in Table 2 below: Table 2

[0033] Carrier combination: From all available carriers, up to three carriers are selected to form a combination based on the UE's capabilities. The preferred combination method will consider the complementary characteristics of carriers in different frequency bands, for example, combining low-frequency carriers with wide coverage with high-frequency carriers with large capacity.

[0034] Transmission mode: Configure specific physical layer transmission parameters for each carrier in the above carrier combination, mainly including: MIMO mode (e.g., transmit diversity, open-loop or closed-loop spatial multiplexing, multi-user MIMO, beamforming), modulation and coding scheme (MCS) level, and power allocation scheme among the carriers.

[0035] Step 103: Based on the multi-dimensional state information, a target carrier configuration strategy is jointly selected for the communication terminal in the current communication scenario from the candidate configuration strategy set through a preset intelligent decision model. The optimization objective of the intelligent decision model is dynamically adapted according to the service type of the communication terminal.

[0036] In the embodiments of this application, the intelligent decision-making model is a machine learning-based decision engine that models the carrier configuration problem as a sequential decision-making process. The input of the intelligent decision-making model is the collected multi-dimensional state information, and its output is the evaluation value of each policy in the candidate configuration policy set.

[0037] Intelligent decision-making models learn optimal decision rules by continuously interacting with the environment (i.e., executing strategies and observing results). Joint selection means that the decision-making of this intelligent decision-making model is cross-layered; it no longer treats the selection of carrier combinations and the configuration of transmission modes as two separate decision-making links, but rather evaluates them as a whole strategy pair.

[0038] The optimization objective is dynamically adapted based on the service type of the communication terminal. This means that the evaluation criteria (i.e., reward function) within the intelligent decision-making model are flexible and variable, and their emphasis automatically adjusts according to different service types of the communication terminal. For example, when the communication terminal service type is enhanced mobile broadband, the optimization objective focuses on maximizing system throughput; when the communication terminal service type is ultra-reliable low-latency communication, the optimization objective focuses on minimizing transmission latency and maximizing transmission reliability; when the communication terminal service type is massive machine-type communication, the optimization objective may focus on improving access success rate and energy efficiency. Through the dynamic adaptation mechanism, the model can jointly select the most suitable target carrier configuration strategy from the candidate configuration strategy set according to the inherent needs of different services, thereby achieving precise resource allocation.

[0039] The process of selecting the target carrier configuration strategy can also be implemented in the following ways, but not limited to: modeling the joint optimization problem of the combination of 3 component carriers (3CC) and the transmission mode as a Markov Decision Process (MDP), and using a reinforcement learning algorithm based on Deep Q-Network (DQN) for real-time, online decision-making.

[0040] Step 104: Configure the corresponding carrier resources and carrier transmission parameters for the communication terminal according to the target carrier configuration strategy.

[0041] In the embodiments of this application, the base station or network control unit allocates a determined carrier combination to the communication terminal according to the target carrier configuration strategy, and activates and sets the corresponding physical layer transmission parameters on each allocated carrier. For example, it applies a specified multiple-input multiple-output mode, adopts a determined modulation and coding strategy level, and allocates transmit power among the carriers according to the weights specified in the strategy. Subsequently, data transmission is initiated based on this configuration, and a new observation period is entered to collect network state changes after the strategy is executed, forming new multi-dimensional state information for subsequent model training and decision optimization, thereby forming a continuously self-improving closed loop.

[0042] This application constructs multi-dimensional state information encompassing terminals, environment, and load, and based on a dynamically generated candidate strategy set, utilizes an intelligent decision-making model with dynamically adaptable optimization targets to perform cross-layer joint decision-making to obtain a target carrier configuration strategy, and finally executes carrier configuration according to the target carrier configuration strategy. This overcomes the shortcomings of traditional solutions, such as rigid strategies, single dimensions, and lack of scenario adaptability, achieving a shift from passive configuration to proactive optimization. It can dynamically and accurately jointly optimize carrier combinations and transmission modes based on real-time heterogeneous scenarios and differentiated service requirements, thereby balancing and meeting the throughput, latency, and reliability requirements of different types of services, and improving the overall network resource utilization efficiency and service quality assurance level.

[0043] In one possible implementation of this application embodiment, when collecting multi-dimensional state information including communication terminal characteristics, network environment characteristics, and network load characteristics in the current communication scenario, it can be implemented in the following ways, but not limited to: collecting communication terminal characteristics, which at least include terminal type, service type of communication service initiated by the communication terminal, quality of service requirements of the communication service, and communication capability of the communication terminal; collecting network environment characteristics, which at least include the channel status of each of multiple available carriers in a preset candidate carrier database; and collecting network load characteristics, which at least include the resource utilization rate of each of multiple available carriers in the preset candidate carrier database, the number of communication terminals, and data transmission latency in the current communication scenario.

[0044] This application combines the service requirements reflected by the characteristics of the communication terminal, the transmission potential reflected by the characteristics of the network environment, and the resource competition status reflected by the characteristics of the network load through refined collection of three dimensions of features. Together, they constitute information that can characterize the current communication scenario status, ensuring that the entire carrier configuration process can make accurate judgments based on a deep understanding of the scenario.

[0045] In one possible implementation of this application embodiment, when selecting a set of candidate configuration strategies from available carriers in the current communication scenario based on the characteristics of the communication terminal, the following methods can be used, but are not limited to: selecting multiple candidate carrier combinations that meet the communication capabilities from the available carriers, and determining the carrier transmission mode corresponding to each of the multiple candidate carrier combinations through a preset carrier-to-transmission mode mapping relationship; determining the first candidate carrier combination and the first carrier transmission mode corresponding to the first candidate carrier combination as the first candidate carrier configuration strategy, wherein the first candidate carrier combination is any one of the multiple candidate carrier combinations; until multiple candidate carrier configuration strategies are determined according to the multiple candidate carrier combinations and the carrier transmission modes corresponding to each of the multiple candidate carrier combinations, a set of candidate configuration strategies is obtained.

[0046] In the embodiments of this application, communication capability refers to the maximum number of carrier aggregations supported by the terminal. Based on this maximum number of carrier aggregations as a constraint, compliant combinations are selected from all available carriers listed in a preset candidate carrier database. For example, if the terminal only supports dual-carrier aggregation, all possible dual-carrier pairings will be generated; if the terminal supports three-carrier aggregation, various combinations, including dual-carrier pairings and the complete set of three carriers, will be generated. Each set of carriers that meets the conditions constitutes a candidate carrier combination. Preset heuristic rules can be incorporated into the generation process, such as prioritizing combinations containing carriers from different frequency bands (e.g., low-frequency and high-frequency bands) to balance coverage and capacity.

[0047] The preset carrier-to-transmission mode mapping relationship is a predefined or learned rule, table, or function that establishes a correlation between specific carrier combination characteristics (such as carrier frequency band, number, and channel condition range) and matching physical layer transmission parameters. When a candidate carrier combination is generated, this mapping relationship is queried to derive or match one or more feasible carrier transmission mode options for that combination.

[0048] Then, the first candidate carrier combination is simply a representative of any one of the multiple generated candidate carrier combinations, and the first carrier transmission mode is the transmission mode determined for that specific combination through a mapping relationship. Binding the two together forms a candidate carrier configuration strategy, namely a specific carrier combination + transmission mode scheme.

[0049] By traversing all generated candidate carrier combinations and determining the corresponding transmission mode for each combination through mapping relationships, multiple independent candidate carrier configuration strategies are formed. The set of all candidate carrier configuration strategies constitutes the candidate configuration strategy set.

[0050] This application adheres to the physical layer capability limitations of the terminal, ensuring that each generated strategy is executable on the terminal side, avoiding invalid or outdated solutions, and guaranteeing the feasibility of the strategy set. By pre-setting the carrier-to-transmission mode mapping relationship, it achieves the pre-association and binding of carrier resource selection and physical layer transmission parameter configuration, enabling subsequent intelligent decision-making models to be evaluated on a unified dimension. This generates multiple possible configuration strategies covering various scenarios under given terminal capabilities and currently available carrier conditions, providing a selection space for the intelligent decision-making model.

[0051] In one possible implementation of this application, each candidate carrier combination consists of up to three available carriers, and the up to three available carriers correspond to different carrier frequency bands and carrier characteristics respectively, so as to perform carrier complementarity. The carrier characteristics include at least carrier coverage and carrier capacity.

[0052] In the embodiments of this application, the limitation of up to three carriers is to ensure compatibility with the three-carrier aggregation technology widely supported by the terminal side in current wireless communication systems. This ensures that the generated candidate carrier configuration strategy matches the hardware capabilities of mainstream terminals, avoiding the generation of too many carrier combinations that the terminal cannot support, thereby improving the efficiency of strategy generation and the pertinence of subsequent decisions.

[0053] Up to three available carriers are designed to correspond to different carrier frequency bands and carrier characteristics, with the aim of carrier complementarity. A carrier frequency band refers to the specific frequency range in which the carrier operates, such as 2.5 GHz, 5 GHz, etc. Radio waves in different carrier frequency bands have different physical propagation characteristics.

[0054] Carrier characteristics are a set of indicators used to characterize the properties of a carrier, including at least carrier coverage and carrier capacity. Carrier coverage represents the propagation range of a carrier signal and its ability to penetrate obstacles. Generally, lower frequency carriers have better coverage due to lower path loss and stronger diffraction capabilities. Carrier capacity represents the maximum data throughput that a carrier can support under ideal conditions. Generally, higher frequency carriers have greater capacity potential because they often have a wider available spectrum bandwidth.

[0055] Carrier complementarity refers to a strategy of combining carriers with different advantageous characteristics to form a combination that outperforms a single carrier or a combination of homogeneous carriers. For example, a carrier combination may include a low-frequency carrier with wide coverage (to ensure the reliability of basic connections and control) and one or two high-frequency carriers with large capacity (to provide high data throughput).

[0056] This application constructs candidate carrier combinations, enabling each generated candidate carrier configuration strategy to possess high performance. By combining different frequency bands and carrier characteristics, high-performance candidate strategies are provided. Through carrier-complementary combinations, the efficiency of carrier configuration is improved, allowing cross-layer joint optimization to be performed within the optimized resource combination space, thereby achieving the goals of improving system throughput and ensuring transmission latency and reliability.

[0057] In one possible implementation of this application embodiment, the carrier transmission mode is used to configure physical layer transmission parameters for each available carrier in the corresponding candidate carrier combination; The carrier transmission mode includes at least multiple-input multiple-output mode, modulation and coding strategy level, and power allocation weight.

[0058] In the embodiments of this application, the carrier transmission mode configures the specific physical layer transmission parameters used for data transmission for each available carrier in the corresponding candidate carrier combination. The transmission mode is a personalized parameter configuration scheme for each carrier.

[0059] In one possible implementation of this application embodiment, the process of jointly selecting a target carrier configuration strategy for the communication terminal in the current communication scenario through a preset intelligent decision model in a set of candidate configuration strategies is a Markov decision process. The state space of the Markov decision process is defined based on multidimensional state information, the action space of the Markov decision process is to dynamically select any candidate carrier configuration strategy from the candidate configuration strategy set, and the reward function of the Markov decision process is a weighted multi-objective function based on service type.

[0060] In the embodiments of this application, the state space of the Markov decision process is defined based on the collected multidimensional state information. Let represent the multidimensional state information at each decision time t. It is represented as a state vector, with each dimension of the state vector directly corresponding to various types of information. For example, the state vector may contain codes representing terminal type (such as one-hot coding), numerical vectors reflecting service quality requirements (such as latency limits, minimum rates), measurements reflecting the state of each available carrier channel (such as Channel Quality Indicator (CQI), RSRP), percentages indicating the utilization of each carrier resource, and data transmission latency characterizing the degree of system congestion.

[0061] The action space of a Markov decision process is defined as the dynamic selection of any candidate carrier configuration strategy from a set of candidate configuration strategies. Each action... This represents a candidate carrier configuration strategy selected at time t. This candidate carrier configuration strategy is a tuple containing a specific carrier combination and its corresponding transmission mode. The dynamic nature of the action space is that the set of candidate configuration strategies is selected based on the real-time terminal communication capabilities; therefore, the set of selectable actions changes dynamically depending on the communication terminal.

[0062] The reward function of a Markov decision process is a weighted multi-objective function based on business type. When the agent performs an action And cause the state to transition Then, an immediate reward value is given to evaluate the quality of the action.

[0063] The reward function is a weighted multi-objective function based on service type. This means that the core logic and weight coefficients of the reward function are switched or adjusted according to the service type of the communication terminal (such as eMBB, URLLC, mMTC). The weighted multi-objective function means that the reward function integrates multiple performance indicators (such as throughput, latency, block error rate, access success rate, energy consumption, etc.) into a single reward value through a weighted approach.

[0064] For eMBB services, function weights will be heavily weighted toward throughput metrics; for URLLC services, the weights will emphasize low latency and high reliability (low block error rate); for mMTC services, the focus may be more on connection success rate and energy efficiency.

[0065] In one possible implementation of this application embodiment, when jointly selecting a target carrier configuration strategy for communication terminals in the current communication scenario, the following methods can be used, but are not limited to: during the Markov decision process, the state space is input into the value evaluation network in the intelligent decision model, and the value evaluation value corresponding to each candidate carrier configuration strategy in the action space is output through the value evaluation network combined with the reward function; the candidate carrier configuration strategy with the highest value evaluation value is selected as the target carrier configuration strategy.

[0066] In the embodiments of this application, the value assessment network is a component of the intelligent decision-making model, such as a deep neural network with a dual-network structure, used to assess the long-term expected cumulative benefits that can be obtained by performing a specific action in a given state.

[0067] The value evaluation network needs to incorporate a reward function to output a value assessment of the configuration strategy for each candidate carrier in the action space. This incorporation doesn't mean dynamically calling the reward function during each forward propagation, but rather that the value evaluation network, through repeated trial and error and backpropagation during long-term training, internalizes the optimization objective defined by the reward function (i.e., the preference for combinations of metrics such as throughput, latency, and reliability under different service types) into its network parameters. The network's forward propagation process, based on its learned knowledge, assesses the current state... Execute every possible action (That is, the prediction of long-term returns when configuring each candidate carrier strategy). The value assessment network is for each... Calculate and output the assessed value, denoted as . The higher this value, the more beneficial it is to achieving the goal oriented by the reward function when choosing this candidate carrier configuration strategy under the current state.

[0068] Finally, the candidate carrier configuration strategy with the highest value assessment score is selected as the target carrier configuration strategy. That is, by comparing the value assessment scores output by the value assessment network for all candidate carrier configuration strategies, the strategy corresponding to the highest value is selected as the target carrier configuration strategy. .

[0069] Strategy This refers to the final selected target carrier configuration strategy.

[0070] Specifically, the Markov Decision Process (MDP) can be described in, but is not limited to, the following manner: The joint optimization problem of carrier combination and transmission mode is modeled as a Markov Decision Process (MDP), and a reinforcement learning algorithm based on Deep Q-Network (DQN) is used for real-time, online decision-making. The specific modeling and decision-making process is as follows: State-space modeling: System state At time t, it is defined as a combination of the following multidimensional vectors.

[0071]

[0072] The terminal type of the communication terminal (e.g., eMBB, URLLC, mMTC) adopts one-hot encoding. Service quality requirements, including latency limits, minimum data rate, and maximum block error rate; Channel state information of the i-th carrier, including CQI, RSRP, SINR, etc. : Physical resource block utilization of the i-th carrier; The average waiting time of the current data packet in the sending queue is the data transmission delay.

[0073] Action space modeling: Action Defined as selecting a policy pair from the dynamic candidate configuration policy set Ase: .

[0074] : A combination of up to 3 carriers selected from the available carriers, such as: {CC1,CC2} or {CC1,CC2,CC3}; Transmission parameters configured for each carrier, including: MIMO mode (e.g., transmit diversity, spatial multiplexing, beamforming); MCS level (e.g., QPSK 1 / 2, 64QAM 3 / 4); and power allocation weight vector. ,satisfy .

[0075] Reward function design: Reward function Designed as a weighted multi-objective function that adapts to business type: Enhance mobile broadband services:

[0076] Ultra-reliable low-latency communication services:

[0077] Massive machine-type communication services:

[0078] in, , , , , , , , All are dynamic weights. For throughput metrics, For transmission delay metrics, For reliability indicators (where, (for block error rate) Packet loss rate / disconnection rate To improve connection success rate, Energy efficiency indicators.

[0079] DQN Network Structure and Decision-Making Process: DQN employs a dual-network structure (including an online network Q and a target network Q'), with its input being the state. The output is for each candidate action. Q value: ; The decision-making process is as follows:

[0080] In one possible implementation of this application embodiment, the terminal type includes at least an enhanced mobile broadband terminal, an ultra-reliable low-latency communication terminal, and a massive machine-type communication terminal, and the service type includes at least an enhanced mobile broadband service, an ultra-reliable low-latency communication service, and a massive machine-type communication service. In response to the service type being enhanced mobile broadband service, the weight of the throughput metric in the reward function is increased. In response to the service type of ultra-reliable low-latency communication, the weights of transmission latency and reliability indicators in the reward function are increased; In response to the business type of large-scale machine communication, the weights of connection success rate and energy efficiency indicators in the reward function are increased.

[0081] In the embodiments of this application, a dynamic weight adjustment mechanism triggered by service type identification aligns the reward function with the inherent needs of the service. This enables the intelligent decision-making model to possess context awareness and target switching capabilities. It solves the problem of mismatch between service needs and resource allocation caused by resource allocation strategies in heterogeneous networks. Through dynamic adjustment of the reward function weights, the model can output a carrier configuration strategy that meets the core requirements of the current specific service, thereby optimizing overall network performance and user experience.

[0082] In one possible implementation of this application embodiment, after configuring the corresponding carrier resources and carrier transmission parameters for the communication terminal according to the target carrier configuration strategy, the following methods may also be used, but are not limited to: obtaining network status information and performance feedback information generated after configuring the corresponding carrier resources and carrier transmission parameters for the communication terminal; and updating the intelligent decision model with the network status information and performance feedback information.

[0083] In one possible implementation of the embodiments of this application, to facilitate understanding of the implementation process of the embodiments of this application, the embodiments of this application also provide a flowchart of another carrier configuration method, such as... Figure 2 As shown, it includes: Step 1: Multidimensional Feature Perception and Information Acquisition. This step forms the data foundation for intelligent decision-making. The system collects and constructs a multidimensional feature state space S in real time.

[0084] Step 2: Construct a dynamic candidate strategy set: Based on the UE characteristics (especially UE capabilities) collected in Step 1, the system generates a dynamic candidate strategy set available at the current moment. Each candidate strategy is a tuple (carrier combination, transmission mode).

[0085] Step 3: Intelligent decision-making based on deep reinforcement learning. The joint optimization problem of 3CC carrier combination and transmission mode is modeled as a Markov Decision Process (MDP), and a reinforcement learning algorithm based on Deep Q-Network (DQN) is used for real-time, online decision-making.

[0086] Step 4: Policy Execution: The base station executes the optimal policy obtained in Step 3, which involves allocating the determined three carriers to the target UE and activating the configured MIMO mode, MCS, and other parameters on each carrier to initiate data transmission. The system then enters an observation period to collect the new network state after policy execution. and the instant rewards obtained .

[0087] Corresponding to the carrier configuration method described above, this application also proposes a carrier configuration apparatus. Since the apparatus embodiments of this application correspond to the method embodiments described above, details not disclosed in the apparatus embodiments can be referred to the method embodiments described above, and will not be repeated here.

[0088] Figure 3 This is a schematic diagram of the structure of a carrier configuration device provided in an embodiment of this application, as shown below. Figure 3 As shown, it includes: The acquisition unit 31 is used to acquire multi-dimensional status information, including communication terminal characteristics, network environment characteristics and network load characteristics, under the current communication scenario. The first selection unit 32 is used to select a candidate configuration strategy set from multiple available carriers in the current communication scenario based on the characteristics of the communication terminal. The candidate configuration strategy set includes multiple candidate carrier configuration strategies, and each candidate carrier configuration strategy includes at least a combination of candidate carriers and a carrier transmission mode. The second selection unit 33 is used to jointly select a target carrier configuration strategy for the communication terminal in the current communication scenario based on multi-dimensional state information and a preset intelligent decision model in the candidate configuration strategy set. The optimization target of the intelligent decision model is dynamically adapted according to the service type of the communication terminal. Configuration unit 34 is used to configure the corresponding carrier resources and carrier transmission parameters for the communication terminal according to the target carrier configuration strategy.

[0089] Furthermore, in one possible implementation of this application embodiment, the acquisition unit 31 is specifically used for: Collect communication terminal characteristics, which include at least the terminal type, the service type of the communication service initiated by the communication terminal, the quality of service requirements of the communication service, and the communication capabilities of the communication terminal. Collect network environment characteristics, which include at least the channel status of multiple available carriers in a preset candidate carrier database; Collect network load characteristics, which include at least the resource utilization rate of multiple available carriers in the preset candidate carrier database, the number of communication terminals, and the data transmission latency in the current communication scenario.

[0090] Furthermore, in one possible implementation of this application embodiment, the first selection unit 32 is specifically used for: Multiple candidate carrier combinations that meet the communication capabilities are selected from the available carriers, and the carrier transmission mode corresponding to each of the multiple candidate carrier combinations is determined by a preset carrier-to-transmission mode mapping relationship. The first candidate carrier combination and the first carrier transmission mode corresponding to the first candidate carrier combination are determined as the first candidate carrier configuration strategy, wherein the first candidate carrier combination is any one of multiple candidate carrier combinations; The process continues until multiple candidate carrier configuration strategies are determined based on multiple candidate carrier combinations and their respective carrier transmission modes, resulting in a candidate configuration strategy set.

[0091] Furthermore, in one possible implementation of the embodiments of this application, each candidate carrier combination consists of at most three available carriers, and the at most three available carriers correspond to different carrier frequency bands and carrier characteristics respectively, so as to perform carrier complementarity, wherein the carrier characteristics include at least carrier coverage and carrier capacity.

[0092] Furthermore, in one possible implementation of this application embodiment, the carrier transmission mode is used to configure physical layer transmission parameters for each available carrier in the corresponding candidate carrier combination; The carrier transmission mode includes at least multiple-input multiple-output mode, modulation and coding strategy level, and power allocation weight.

[0093] Furthermore, in one possible implementation of this application embodiment, the process of jointly selecting a target carrier configuration strategy for the communication terminal in the current communication scenario through a preset intelligent decision-making model in the candidate configuration strategy set is a Markov decision process. The state space of the Markov decision process is defined based on multidimensional state information, the action space of the Markov decision process is to dynamically select any candidate carrier configuration strategy from the candidate configuration strategy set, and the reward function of the Markov decision process is a weighted multi-objective function based on service type.

[0094] Furthermore, in one possible implementation of this application embodiment, the second selection unit 33 is specifically used for: In the Markov decision-making process, the state space is input into the value evaluation network in the intelligent decision-making model, and the value evaluation value corresponding to each candidate carrier configuration strategy in the action space is output by combining the value evaluation network with the reward function. The candidate carrier configuration strategy with the highest value assessment value is selected as the target carrier configuration strategy.

[0095] Furthermore, in one possible implementation of the embodiments of this application, the terminal type includes at least an enhanced mobile broadband terminal, an ultra-reliable low-latency communication terminal, and a massive machine-type communication terminal, and the service type includes at least an enhanced mobile broadband service, an ultra-reliable low-latency communication service, and a massive machine-type communication service. In response to the service type being enhanced mobile broadband service, the weight of the throughput metric in the reward function is increased. In response to the service type of ultra-reliable low-latency communication, the weights of transmission latency and reliability indicators in the reward function are increased; In response to the business type of large-scale machine communication, the weights of connection success rate and energy efficiency indicators in the reward function are increased.

[0096] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this application, and the principle is the same. Therefore, the embodiments of this application are not limited thereto.

[0097] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0098] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0099] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0100] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0101] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as carrier configuration methods. For example, in some embodiments, the carrier configuration method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned carrier configuration method by any other suitable means (e.g., by means of firmware).

[0102] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0103] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0104] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0105] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0106] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0107] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0108] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0109] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0110] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A carrier configuration method, characterized in that, include: Collect multi-dimensional status information in the current communication scenario, including communication terminal characteristics, network environment characteristics, and network load characteristics; Based on the characteristics of the communication terminal, a candidate configuration strategy set is selected from multiple available carriers in the current communication scenario. The candidate configuration strategy set includes multiple candidate carrier configuration strategies, and each candidate carrier configuration strategy includes at least a combination of candidate carriers and a carrier transmission mode. Based on the multidimensional state information, a preset intelligent decision-making model is used to jointly select a target carrier configuration strategy for the communication terminal in the current communication scenario from the candidate configuration strategy set. The optimization objective of the intelligent decision-making model is dynamically adapted according to the service type of the communication terminal. Configure the corresponding carrier resources and carrier transmission parameters for the communication terminal according to the target carrier configuration strategy.

2. The carrier configuration method according to claim 1, characterized in that, The collection of multi-dimensional state information, including communication terminal characteristics, network environment characteristics, and network load characteristics, under the current communication scenario includes: The characteristics of the communication terminal are collected, including at least the terminal type, the service type of the communication service initiated by the communication terminal, the quality of service requirements of the communication service, and the communication capabilities of the communication terminal. The network environment features are collected, and the network environment features include at least the channel states of the multiple available carriers in the preset candidate carrier database; The network load characteristics are collected, which include at least the resource utilization rate of each of the multiple available carriers in the preset candidate carrier database, the number of communication terminals, and the data transmission latency in the current communication scenario.

3. The carrier configuration method according to claim 2, characterized in that, The step of selecting a candidate configuration strategy set from available carriers in the current communication scenario based on the characteristics of the communication terminal includes: Select multiple candidate carrier combinations that satisfy the communication capability from the available carriers, and determine the carrier transmission mode corresponding to each of the multiple candidate carrier combinations through a preset carrier-to-transmission mode mapping relationship; The first candidate carrier combination and the first carrier transmission mode corresponding to the first candidate carrier combination are determined as the first candidate carrier configuration strategy, wherein the first candidate carrier combination is any one of the multiple candidate carrier combinations; The candidate carrier configuration strategy set is obtained by determining multiple candidate carrier configuration strategies based on multiple candidate carrier combinations and the carrier transmission modes corresponding to each of the multiple candidate carrier combinations.

4. The carrier configuration method according to claim 3, characterized in that, Each candidate carrier combination consists of up to three available carriers, each of which corresponds to a different carrier frequency band and carrier characteristics, for carrier complementarity. The carrier characteristics include at least carrier coverage and carrier capacity.

5. The carrier configuration method according to claim 3, characterized in that, The carrier transmission mode is used to configure physical layer transmission parameters for each available carrier in the corresponding candidate carrier combination; The carrier transmission mode includes at least multiple-input multiple-output mode, modulation and coding strategy level, and power allocation weight.

6. The carrier configuration method according to claim 2, characterized in that, The process of jointly selecting a target carrier configuration strategy for the communication terminal in the current communication scenario using a preset intelligent decision-making model in the candidate configuration strategy set is a Markov decision process. The state space of the Markov decision process is defined based on the multidimensional state information, the action space of the Markov decision process is to dynamically select any candidate carrier configuration strategy from the candidate configuration strategy set, and the reward function of the Markov decision process is a weighted multi-objective function based on the service type.

7. The carrier configuration method according to claim 6, characterized in that, The step of jointly selecting a target carrier configuration strategy for the communication terminal in the current communication scenario from the candidate configuration strategy set through a preset intelligent decision-making model includes: In the Markov decision-making process, the state space is input into the value evaluation network in the intelligent decision-making model, and the value evaluation value corresponding to each candidate carrier configuration strategy in the action space is output through the value evaluation network in combination with the reward function. The candidate carrier configuration strategy with the highest value assessment value is selected as the target carrier configuration strategy.

8. The carrier configuration method according to claim 6, characterized in that, The terminal types include at least enhanced mobile broadband terminals, ultra-reliable low-latency communication terminals, and massive machine-type communication terminals; the service types include at least enhanced mobile broadband services, ultra-reliable low-latency communication services, and massive machine-type communication services. In response to the fact that the service type is enhanced mobile broadband service, the weight corresponding to the throughput indicator in the reward function is increased; In response to the fact that the service type is ultra-reliable low-latency communication service, the weights of transmission latency and reliability indicators in the reward function are increased; In response to the fact that the service type is a large-scale machine communication service, the weights of connection success rate and energy efficiency indicators in the reward function are increased.

9. A carrier configuration device, characterized in that, include: The acquisition unit is used to acquire multi-dimensional status information, including communication terminal characteristics, network environment characteristics, and network load characteristics, under the current communication scenario. The first selection unit is configured to select a set of candidate configuration strategies from multiple available carriers in the current communication scenario based on the characteristics of the communication terminal. The set of candidate configuration strategies includes multiple candidate carrier configuration strategies, and each candidate carrier configuration strategy includes at least a combination of candidate carriers and a carrier transmission mode. The second selection unit is used to jointly select a target carrier configuration strategy for the communication terminal in the current communication scenario based on the multi-dimensional state information and through a preset intelligent decision model in the candidate configuration strategy set, wherein the optimization objective of the intelligent decision model is dynamically adapted according to the service type of the communication terminal. The configuration unit is used to configure the corresponding carrier resources and carrier transmission parameters for the communication terminal according to the target carrier configuration strategy.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

Images